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

Head-to-Head Benchmarks

The data is unambiguous: the NVIDIA GeForce RTX 2080 SUPER wins all ten head-to-head benchmark comparisons against the AMD Radeon RX 6700M. The largest margin comes in Passmark G2D, where the RTX 2080 SUPER scores 920 versus 555 for the RX 6700M, a 39.7% advantage. That is the single biggest gap in the entire comparison, and it signals a fundamental difference in how these two GPUs handle 2D workloads.

DirectX 10 and DirectX 9 results are also heavily skewed toward NVIDIA. The RTX 2080 SUPER posts 140 in Passmark DirectX 10 against 92 for the AMD part, a 34.3% lead. In DirectX 9, the gap is 31.7% (227 versus 155). These older API tests reward the NVIDIA architecture's raw throughput, and the margin is consistent across both legacy DirectX versions.

Compute performance tells a similar story. The RTX 2080 SUPER scores 8290 in Passmark GPU Compute, while the RX 6700M manages only 5191 — a 37.4% deficit. Geekbench OpenCL narrows the gap slightly, with NVIDIA leading 99226 to 77666 (21.7% ahead). Vulkan results are closer still but remain firmly in NVIDIA's favor: 111284 versus 90816, an 18.4% lead.

The most modern test in the suite, 3DMark Steel Nomad DX12, is the tightest contest. The RTX 2080 SUPER wins with 1882 against 1845, a mere 2% margin. This suggests that in current-generation DirectX 12 titles, the two GPUs are nearly equivalent in raw rasterization performance, even though NVIDIA still takes the win.

Passmark DirectX 11 and DirectX 12 results complete the sweep. DirectX 11 shows NVIDIA ahead by 21.8% (165 versus 129), while DirectX 12 shows a smaller 13.3% lead (75 versus 65). The overall pattern is clear: NVIDIA wins every test, with margins ranging from 2% to nearly 40%. The RX 6700M's average benchmark score of 25633 actually exceeds the RTX 2080 SUPER's 24170, but that average includes Geekbench Metal (91911), a test where NVIDIA has no comparable result, skewing the aggregate in AMD's favor.

Architecture Differences

The two GPUs come from fundamentally different design philosophies. The AMD Radeon RX 6700M uses the Navi 22 chip built on RDNA 2.0 architecture, manufactured on a 7 nm process at TSMC. The NVIDIA GeForce RTX 2080 SUPER uses the TU104 chip with Turing architecture, manufactured on a 12 nm process, also at TSMC. The process node difference is significant — 7 nm versus 12 nm — and it directly explains the transistor density gap: AMD packs 51.3 million transistors per square millimeter versus NVIDIA's 25.0 million.

Die size tells the opposite story. The NVIDIA chip is considerably larger at 545 mm² versus 335 mm² for AMD, but AMD's higher density allows it to fit 17,200 million transistors on that smaller die, compared to 13,600 million on NVIDIA's larger chip. This is a classic case of a newer, denser process enabling more complex logic in a smaller footprint.

Clock speeds differ notably. The RX 6700M has a base clock of 1489 MHz and a boost clock of 2400 MHz, with a game clock of 2300 MHz. The RTX 2080 SUPER runs a higher base clock of 1650 MHz but a lower boost clock of 1815 MHz. AMD's boost advantage of 585 MHz is substantial on paper, yet it does not translate into benchmark wins, suggesting NVIDIA's architecture extracts more performance per clock in most workloads.

Memory configurations are also distinct. The RX 6700M offers 10 GB of GDDR6 on a 160-bit bus, achieving 320.0 GB/s bandwidth. The RTX 2080 SUPER has 8 GB of GDDR6 on a 256-bit bus, delivering 495.9 GB/s — a 55% bandwidth advantage. Memory clock speeds are close (2000 MHz for AMD versus 1937 MHz for NVIDIA), but the wider bus is decisive.

Compute unit counts favor NVIDIA in raw numbers. The RTX 2080 SUPER has 3072 shading units, 192 texture mapping units, 48 ray tracing cores, and 384 tensor cores. The RX 6700M has 2304 shading units, 144 TMUs, and 36 ray tracing cores, with no tensor cores listed. Both GPUs have 64 ROPs. Despite fewer units, the RX 6700M achieves nearly identical FP32 performance: 11.06 TFLOPS versus 11.15 TFLOPS for NVIDIA. FP16 is similarly close at 22.12 TFLOPS versus 22.30 TFLOPS.

Power and physical design diverge sharply. The RX 6700M is an integrated graphics package (IGP) with no power connectors and a 135 W TDP. The RTX 2080 SUPER is a dual-slot card with 1x 6-pin and 1x 8-pin power connectors, a 250 W TDP, and a suggested PSU of 600 W. The NVIDIA card measures 267 mm in length, 116 mm in height, and 35 mm in width. The RX 6700M's display outputs are "portable device dependent," while the RTX 2080 SUPER offers 1x HDMI 2.0, 3x DisplayPort 1.4a, and 1x USB Type-C.

Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The bus interface differs: PCIe 4.0 x16 for AMD versus PCIe 3.0 x16 for NVIDIA.

The Verdict

The benchmark data delivers a clear verdict: the NVIDIA GeForce RTX 2080 SUPER is the superior performer across every tested workload. With ten wins out of ten head-to-head comparisons, there is no ambiguity. The RX 6700M never takes a single benchmark, and its average score advantage (25633 versus 24170) is an artifact of the Geekbench Metal result, which NVIDIA does not participate in.

The RTX 2080 SUPER's largest advantages are in 2D performance (39.7% in G2D), compute (37.4% in GPU Compute), and legacy DirectX (34.3% in DirectX 10, 31.7% in DirectX 9). These are not marginal wins; they represent a substantial architectural edge in specific workload categories. The narrowest margin is in 3DMark Steel Nomad DX12, where NVIDIA leads by just 2%, indicating that modern DirectX 12 games will see near-parity performance.

For buyers prioritizing compute-heavy tasks, older DirectX titles, or 2D applications, the RTX 2080 SUPER is the clear choice. For those focused exclusively on current DirectX 12 games, the difference is small enough that other factors — such as the RX 6700M's lower 135 W TDP versus 250 W, or its IGP form factor — might tip the decision. But strictly from benchmark performance, NVIDIA wins.

The RX 6700M's 71st percentile versus the RTX 2080 SUPER's 69th percentile among all GPUs is misleading in this context. The percentile rankings reflect the full benchmark suite including Metal, but the head-to-head data shows NVIDIA ahead in every common test. The nearest rivals data corroborates this: the RX 6700M sits near the RTX 3080 Ti Mobile (0.4% lower average score) and AMD FirePro D700 (0.8% lower), while the RTX 2080 SUPER is close to the GTX 780 Ti (0.3% lower) and RX 6600 XT (1.1% lower).

Specification Differences

| Field | AMD Radeon RX 6700M | NVIDIA GeForce RTX 2080 SUPER |

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

| Architecture | RDNA 2.0 | Turing |

| Process Node | 7 nm | 12 nm |

| Transistors | 17,200 million | 13,600 million |

| Die Size | 335 mm² | 545 mm² |

| Transistor Density | 51.3M / mm² | 25.0M / mm² |

| Base Clock | 1489 MHz | 1650 MHz |

| Boost Clock | 2400 MHz | 1815 MHz |

| Memory Size | 10 GB | 8 GB |

| Memory Bus Width | 160 bit | 256 bit |

| Memory Bandwidth | 320.0 GB/s | 495.9 GB/s |

| Shading Units | 2304 | 3072 |

| TMUs | 144 | 192 |

| RT Cores | 36 | 48 |

| Tensor Cores | None listed | 384 |

| Pixel Rate | 153.6 GPixel/s | 116.2 GPixel/s |

| Texture Rate | 345.6 GTexel/s | 348.5 GTexel/s |

| TDP | 135 W | 250 W |

| Slot Width | IGP | Dual-slot |

| Power Connectors | None | 1x 6-pin + 1x 8-pin |

| Bus Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |

| Display Outputs | Portable Device Dependent | 1x HDMI 2.0, 3x DisplayPort 1.4a, 1x USB Type-C |

| Launch MSRP | Not available | 699 USD (stated once) |

FAQ

Q: Which GPU has more memory bandwidth?

A: The NVIDIA GeForce RTX 2080 SUPER has 495.9 GB/s bandwidth versus 320.0 GB/s for the AMD Radeon RX 6700M, due to its 256-bit bus compared to 160-bit.

Q: Does the RX 6700M win any benchmark?

A: No. The head-to-head data shows the RTX 2080 SUPER winning all ten tests, with no wins for the RX 6700M.

Q: Why does the RX 6700M have a higher average benchmark score?

A: The RX 6700M's average of 25633 includes a Geekbench Metal score of 91911, a test the RTX 2080 SUPER does not have a result for. The RTX 2080 SUPER's average is 24170.

Q: What is the closest benchmark result between the two?

A: 3DMark Steel Nomad DX12, where the RTX 2080 SUPER scores 1882 versus 1845 for the RX 6700M, a 2% margin.

Q: Which GPU has more shading units?

A: The RTX 2080 SUPER has 3072 shading units, while the RX 6700M has 2304, yet their FP32 performance is nearly identical at 11.15 TFLOPS versus 11.06 TFLOPS.

Q: What is the power consumption difference?

A: The RX 6700M has a 135 W TDP, while the RTX 2080 SUPER has a 250 W TDP. The NVIDIA card also requires a 600 W suggested PSU and dual power connectors.

Where Each One Wins

The RTX 2080 SUPER wins every category where both GPUs have benchmark results. Its most decisive victories are in 2D performance (Passmark G2D, 39.7% ahead), compute workloads (Passmark GPU Compute, 37.4% ahead), and legacy DirectX APIs (DirectX 10 at 34.3%, DirectX 9 at 31.7%). These results make it the preferred option for professional 2D applications, GPU compute tasks, and older game libraries that rely on DirectX 9 or 10.

The RX 6700M's only theoretical advantages are structural rather than performance-based. Its 10 GB memory capacity exceeds the RTX 2080 SUPER's 8 GB, which could matter in texture-heavy workloads that exceed 8 GB. Its 135 W TDP is nearly half the NVIDIA card's 250 W, making it far more power-efficient on paper. The IGP form factor means no power connectors are needed, simplifying installation in portable devices.

In modern DirectX 12 workloads, the gap nearly disappears. The 3DMark Steel Nomad result of 2% suggests that for current-generation games, the two GPUs are effectively interchangeable in performance. The RTX 2080 SUPER's 18.4% lead in Vulkan and 21.7% lead in OpenCL, however, show that NVIDIA maintains an advantage in cross-platform graphics APIs.

For a desktop user with a 600 W PSU and room for a dual-slot card, the RTX 2080 SUPER is the data-backed choice. For a portable device constrained by power and physical space, the RX 6700M's IGP design and 135 W TDP are compelling, but the performance trade-off is substantial in every measured test. The verdict is straightforward: NVIDIA wins on performance, AMD wins on efficiency and form factor.