AMD Radeon RX 6700 vs NVIDIA GeForce GTX 980 Ti Comparison

The AMD Radeon RX 6700 and the NVIDIA GeForce GTX 980 Ti represent two distinct eras of graphics hardware, separated by six years of architectural evolution. The benchmark data available shows a decisive performance gap, with the RX 6700 winning all four head-to-head comparisons, but the nature of those wins—and the specific workloads where they occur—reveals a more nuanced picture than a simple generational upgrade. This analysis breaks down the data by workload, architecture, and specification to clarify where each card stands.

Where Each One Wins

Based on the head-to-head benchmark results, the AMD Radeon RX 6700 wins every single comparison. There are no benchmark categories where the GTX 980 Ti comes out ahead. The RX 6700's wins span both modern and legacy API workloads, from DirectX 12 to Vulkan to OpenCL, indicating a comprehensive advantage rather than a narrow specialization.

The most extreme disparity appears in the Geekbench Metal test, where the RX 6700 scores 122,223 points against the GTX 980 Ti's 19,520 points. This 526.1% delta is by far the largest margin in the dataset, suggesting the RX 6700 has a massive advantage in Apple's Metal API environment. The Geekbench OpenCL test shows a similarly lopsided result, with the RX 6700 at 97,841 versus 43,513 for the GTX 980 Ti, a 124.9% difference. These compute-oriented benchmarks highlight the RX 6700's superior raw processing capabilities.

In gaming-focused workloads, the margins narrow but remain decisive. The 3DMark Steel Nomad DX12 test gives the RX 6700 a 2014 score against 1321 for the GTX 980 Ti, a 52.5% advantage. The Geekbench Vulkan test shows the RX 6700 at 83,974 versus 47,724, a 76% lead. While the GTX 980 Ti is competitive in relative terms on these tests compared to the Metal and OpenCL results, it still trails by a significant margin. The data indicates the RX 6700 is the clear winner across every measured workload, with no scenario where the older card can claim victory.

Architecture Differences

The architectural gap between these two cards is substantial, explaining the performance disparity. The RX 6700 uses the Navi 22 chip built on RDNA 2.0 architecture, manufactured on a 7 nm process at TSMC. The GTX 980 Ti uses the GM200 chip on Maxwell 2.0 architecture, built on a much older 28 nm process, also at TSMC. This process difference is stark: 7 nm versus 28 nm, which directly impacts transistor density and power efficiency.

The RX 6700 packs 17,200 million transistors into a 335 mm² die, yielding a density of 51.3 million transistors per square millimeter. The GTX 980 Ti has 8,000 million transistors spread across a much larger 601 mm² die, giving it a density of just 13.3 million transistors per square millimeter. The RX 6700 achieves nearly four times the transistor density, enabling more compute units and features in a smaller physical footprint.

Memory configurations also diverge significantly. The RX 6700 uses 10 GB of GDDR6 memory on a 160-bit bus, delivering 320.0 GB/s of bandwidth. The GTX 980 Ti uses 6 GB of GDDR5 memory on a wider 384-bit bus, achieving a slightly higher 336.6 GB/s bandwidth. The RX 6700 compensates for its narrower bus with faster GDDR6 memory running at 16 Gbps effective, while the GTX 980 Ti's GDDR5 runs at 7 Gbps effective.

Feature support is another major differentiator. The RX 6700 includes 36 dedicated ray tracing cores, a feature entirely absent from the GTX 980 Ti. The RX 6700 also supports DirectX 12 Ultimate (12_2), while the GTX 980 Ti is limited to DirectX 12 (12_1). Both cards support OpenGL 4.6 and Vulkan 1.4, but the RX 6700's newer architecture enables hardware-accelerated ray tracing and other DirectX 12 Ultimate features that the Maxwell-based card cannot handle.

Head-to-Head Benchmarks

The 3DMark Steel Nomad DX12 test provides the most gaming-relevant comparison. The RX 6700 scores 2014, while the GTX 980 Ti scores 1321, giving the RX 6700 a 52.5% advantage. This test stresses modern DirectX 12 rendering paths, where the RX 6700's RDNA 2 architecture and ray tracing cores provide a substantial edge. The GTX 980 Ti's Maxwell architecture, designed for an earlier generation of DirectX, struggles to keep pace in this workload.

The Geekbench Metal benchmark shows the largest gap between the two cards. The RX 6700's 122,223 score dwarfs the GTX 980 Ti's 19,520, a 526.1% difference. This is a compute-heavy test that heavily favors the RX 6700's 11.29 TFLOPS of FP32 performance against the GTX 980 Ti's 6.060 TFLOPS. The RX 6700 also has 2304 shading units compared to the GTX 980 Ti's 2816, but the newer architecture and higher clock speeds—2450 MHz boost versus 1076 MHz boost—more than compensate for the lower core count.

Geekbench OpenCL results follow a similar pattern. The RX 6700 scores 97,841 against the GTX 980 Ti's 43,513, a 124.9% advantage. This test exercises general-purpose GPU compute, where the RX 6700's RDNA 2 architecture with its 22.58 TFLOPS of FP16 performance (2:1 ratio) and higher texture rate of 352.8 GTexel/s versus 189.4 GTexel/s gives it a clear edge. The GTX 980 Ti has no FP16 support listed, further limiting its compute capabilities.

The Geekbench Vulkan test shows the RX 6700 with 83,974 points against the GTX 980 Ti's 47,724, a 76% lead. Vulkan is a modern cross-platform graphics API, and the RX 6700's newer architecture handles it more efficiently. The RX 6700's pixel rate of 156.8 GPixel/s versus the GTX 980 Ti's 103.3 GPixel/s contributes to this advantage, as does the higher memory bandwidth relative to the memory size and the faster effective memory clock speed.

The Verdict

The data clearly indicates that the AMD Radeon RX 6700 is the superior performer across all measured benchmarks. Anyone choosing between these two cards for gaming or compute workloads should select the RX 6700, as it wins every head-to-head comparison by margins ranging from 52.5% to 526.1%. The RX 6700 also offers modern features like hardware ray tracing and DirectX 12 Ultimate support that the GTX 980 Ti cannot provide.

The GTX 980 Ti, while historically significant as a high-end card from the Maxwell era, is decisively outclassed in this comparison. Its only advantages are a slightly higher memory bandwidth (336.6 GB/s versus 320.0 GB/s) and a wider 384-bit memory bus, but these do not translate into any benchmark wins. The RX 6700's higher clock speeds, newer architecture, and superior compute performance make it the clear choice for any modern workload.

For users considering a used or legacy system, the GTX 980 Ti might still function for older games or light workloads, but the data shows it trails the RX 6700 by massive margins in every category. The RX 6700's 75th percentile ranking among all GPUs, compared to the GTX 980 Ti's 73rd percentile, further confirms the newer card's overall superiority. The RX 6700's average benchmark score of 30,433 versus the GTX 980 Ti's 28,020 reinforces this conclusion, despite the RX 6700's nearest rivals including the NVIDIA RTX 3070 Ti with a 1.6% delta and the AMD RX 6800 with a 1.1% delta.

FAQ

Q: Which card performs better in DirectX 12 gaming workloads?

A: The AMD Radeon RX 6700 scores 2014 in the 3DMark Steel Nomad DX12 test, which is 52.5% higher than the NVIDIA GeForce GTX 980 Ti's score of 1321. The RX 6700 also supports DirectX 12 Ultimate (12_2), while the GTX 980 Ti is limited to DirectX 12 (12_1).

Q: How significant is the compute performance gap between these two cards?

A: The gap is substantial. In Geekbench OpenCL, the RX 6700 scores 97,841 against the GTX 980 Ti's 43,513, a 124.9% advantage. The RX 6700 also has 11.29 TFLOPS of FP32 performance compared to the GTX 980 Ti's 6.060 TFLOPS.

Q: Does the GTX 980 Ti have any architectural advantages over the RX 6700?

A: The GTX 980 Ti has a wider 384-bit memory bus and slightly higher memory bandwidth at 336.6 GB/s versus 320.0 GB/s for the RX 6700. However, this does not result in any benchmark wins, as the RX 6700 wins all four head-to-head comparisons.

Q: What is the difference in memory capacity and type?

A: The RX 6700 has 10 GB of GDDR6 memory, while the GTX 980 Ti has 6 GB of GDDR5 memory. The RX 6700's memory runs at 16 Gbps effective, compared to the GTX 980 Ti's 7 Gbps effective, though the GTX 980 Ti's wider bus keeps its bandwidth competitive.

Q: Which card has better feature support for modern games?

A: The RX 6700 includes 36 ray tracing cores and supports DirectX 12 Ultimate (12_2), enabling hardware-accelerated ray tracing. The GTX 980 Ti has no ray tracing cores and is limited to DirectX 12 (12_1), so it cannot handle these modern features.

Q: How do the two cards compare in Vulkan performance?

A: The RX 6700 scores 83,974 in Geekbench Vulkan, which is 76% higher than the GTX 980 Ti's 47,724. Both cards support Vulkan 1.4, but the RX 6700's newer architecture delivers significantly better performance in this API.

Specification Differences

The following specifications differ between the two cards:

| Specification | AMD Radeon RX 6700 | NVIDIA GeForce GTX 980 Ti |

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

| Architecture | RDNA 2.0 | Maxwell 2.0 |

| Process Node | 7 nm | 28 nm |

| Transistors | 17,200 million | 8,000 million |

| Die Size | 335 mm² | 601 mm² |

| Transistor Density | 51.3M / mm² | 13.3M / mm² |

| Base Clock | 1941 MHz | 1000 MHz |

| Boost Clock | 2450 MHz | 1076 MHz |

| Game Clock | 2174 MHz | N/A |

| Memory Clock | 2000 MHz (16 Gbps effective) | 1753 MHz (7 Gbps effective) |

| Memory Size | 10 GB | 6 GB |

| Memory Type | GDDR6 | GDDR5 |

| Memory Bus Width | 160 bit | 384 bit |

| Memory Bandwidth | 320.0 GB/s | 336.6 GB/s |

| Shading Units | 2304 | 2816 |

| TMUs | 144 | 176 |

| ROPs | 64 | 96 |

| Ray Tracing Cores | 36 | N/A |

| Pixel Rate | 156.8 GPixel/s | 103.3 GPixel/s |

| Texture Rate | 352.8 GTexel/s | 189.4 GTexel/s |

| FP32 Performance | 11.29 TFLOPS | 6.060 TFLOPS |

| FP16 Performance | 22.58 TFLOPS (2:1) | N/A |

| TDP | 175 W | 250 W |

| Power Connectors | 1x 8-pin | 1x 6-pin + 1x 8-pin |

| Suggested PSU | 450 W | 600 W |

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

| Display Outputs | 1x HDMI 2.1, 3x DisplayPort 1.4a | 1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.2 |

| DirectX Support | 12 Ultimate (12_2) | 12 (12_1) |

| Release Date | 2021-06-08 | 2015-06-01 |

| Height | 110 mm (4.3 inches) | 111 mm (4.4 inches) |