NVIDIA GeForce GTX 1080 Ti vs NVIDIA GeForce RTX 2060 SUPER Comparison

The recorded data shows a clear generational clash. The GeForce RTX 2060 SUPER, built on the newer Turing architecture, and the GeForce GTX 1080 Ti, a Pascal flagship, trade blows across different workloads. Benchmark results indicate that the GTX 1080 Ti holds a commanding lead in most traditional rasterization tests, while the RTX 2060 SUPER demonstrates superiority in compute-oriented and API-specific scenarios. The average benchmark score of 18,093 for the RTX 2060 SUPER versus 15,548 for the GTX 1080 Ti, however, paints a more nuanced picture than the raw head-to-head wins suggest.

Head-to-Head Benchmarks

The most decisive victory for the RTX 2060 SUPER comes in the Geekbench Vulkan test. Here, the Turing card scores 77,402, which is 91.1% higher than the GTX 1080 Ti’s 40,511. This is an exceptional margin, indicating a massive advantage in this specific low-level API workload. Similarly, in Geekbench OpenCL, the RTX 2060 SUPER outperforms the GTX 1080 Ti by 13.3%, with scores of 76,957 and 67,929 respectively. These two wins account for the RTX 2060 SUPER’s total of 2 victories in the head-to-head comparison.

The GTX 1080 Ti, conversely, wins the remaining 8 benchmarks. Its largest margin of victory is in Passmark GPU Compute, where it scores 9,632 against the RTX 2060 SUPER’s 6,721, a substantial 30.2% advantage. This suggests that the Pascal card has a significant edge in pure compute throughput, likely due to its higher raw shader count. In the 3DMark Steel Nomad DX12 test, the GTX 1080 Ti also comes out ahead, scoring 2,231 versus 2,011, a 9.9% lead. The Passmark G3D test shows a similar pattern, with the GTX 1080 Ti scoring 18,600 compared to 16,462, an 11.5% difference.

The legacy DirectX tests further favor the GTX 1080 Ti. In Passmark DirectX 11, the older card leads by 13.9%, scoring 151 against 130. The DirectX 10 test shows a smaller 5.9% gap, with scores of 118 and 111. Even in DirectX 9, the GTX 1080 Ti wins by 5.6%, scoring 231 versus 218. The DirectX 12 test results are closer, with the GTX 1080 Ti scoring 66 against the RTX 2060 SUPER’s 61, a 7.6% difference. Finally, in the 2D graphics test (Passmark G2D), the GTX 1080 Ti scores 939, which is 9.1% higher than the RTX 2060 SUPER’s 854.

Where Each One Wins

The data suggests a clear split in workload types. The GTX 1080 Ti is the stronger performer for traditional, API-bound gaming workloads, particularly those relying on DirectX 11, DirectX 9, and even DirectX 12. Its wins in 3DMark Steel Nomad, Passmark G3D, and all the Passmark DirectX variants indicate that it delivers higher frame rates in most standard game engines. The 30.2% lead in Passmark GPU Compute also points to its strength in general-purpose compute tasks, such as rendering or physics simulations that leverage raw FP32 power.

The RTX 2060 SUPER wins where modern APIs and compute-specific optimizations come into play. The 91.1% lead in Geekbench Vulkan is the standout result. This indicates that in Vulkan-based titles, the Turing architecture’s design provides a dramatic boost. The 13.3% lead in Geekbench OpenCL also shows an advantage in heterogeneous computing environments. These wins suggest that the RTX 2060 SUPER is better suited for emerging workloads that take advantage of newer programming interfaces and the specific scheduling features of the Turing architecture.

Architecture Differences

The two cards are built on fundamentally different architectures and manufacturing processes. The RTX 2060 SUPER uses the TU106 chip on a 12 nm process at TSMC, with 10,800 million transistors on a 445 mm² die. This results in a transistor density of 24.3M per mm². The GTX 1080 Ti, in contrast, uses the GP102 chip on a larger 16 nm process, packing 11,800 million transistors into a 471 mm² die, for a density of 25.1M per mm². Despite the smaller node, the RTX 2060 SUPER has a lower transistor count and lower density than its predecessor.

The compute configurations differ significantly. The RTX 2060 SUPER has 2,176 shading units, 136 texture mapping units (TMUs), and 64 ROPs. It also introduces dedicated hardware: 34 RT cores for ray tracing and 272 tensor cores for AI acceleration. The GTX 1080 Ti has a much higher count of 3,584 shading units, 224 TMUs, and 88 ROPs, but it lacks RT and tensor cores entirely. This explains the raw rasterization advantage of the GTX 1080 Ti, which offers 11.34 TFLOPS of FP32 compute versus 7.181 TFLOPS for the RTX 2060 SUPER. The pixel rate also favors the GTX 1080 Ti at 139.2 GPixel/s versus 105.6 GPixel/s, as does the texture rate at 354.4 GTexel/s versus 224.4 GTexel/s.

Memory subsystems also differ. The RTX 2060 SUPER has 8 GB of GDDR6 on a 256-bit bus, delivering 448.0 GB/s of bandwidth. The GTX 1080 Ti has 11 GB of GDDR5X on a wider 352-bit bus, providing 484.4 GB/s. The clock speeds show the GTX 1080 Ti boosts slightly higher at 1582 MHz versus 1650 MHz for the RTX 2060 SUPER, but the memory clock is faster on the newer card at 1750 MHz (14 Gbps effective) versus 1376 MHz (11 Gbps effective). The power characteristics differ as well, with the RTX 2060 SUPER rated at 175 W TDP and a suggested 450 W PSU, while the GTX 1080 Ti is rated at 250 W TDP with a suggested 600 W PSU.

FAQ

Q: Which card is faster in the 3DMark Steel Nomad DX12 benchmark?

A: The GeForce GTX 1080 Ti scores 2,231 in that test, which is 9.9% higher than the GeForce RTX 2060 SUPER’s 2,011.

Q: How large is the performance gap in Vulkan compute workloads?

A: The GeForce RTX 2060 SUPER leads by a massive 91.1% in the Geekbench Vulkan test, scoring 77,402 against the GTX 1080 Ti’s 40,511.

Q: Does the GTX 1080 Ti have better raw compute performance?

A: Yes, the data shows a 30.2% lead for the GTX 1080 Ti in the Passmark GPU Compute test, with a score of 9,632 versus 6,721 for the RTX 2060 SUPER.

Q: Which card has a higher average benchmark score?

A: The RTX 2060 SUPER has a higher average benchmark score of 18,093, while the GTX 1080 Ti averages 15,548.

Q: Are there any legacy API tests where the RTX 2060 SUPER wins?

A: No, the GTX 1080 Ti wins all four Passmark DirectX tests (9, 10, 11, and 12), with margins ranging from 5.6% to 13.9%.

Q: What is the difference in memory bandwidth?

A: The GTX 1080 Ti has a higher memory bandwidth of 484.4 GB/s, while the RTX 2060 SUPER has 448.0 GB/s.

The Verdict

Based strictly on the recorded data, the GeForce GTX 1080 Ti is the superior card for most gaming scenarios. Its wins in the 3DMark Steel Nomad, Passmark G3D, and all DirectX tests indicate that it will provide higher frame rates in the majority of existing game titles. The 30.2% lead in compute performance also makes it a better choice for users who rely on GPU compute for rendering or other professional tasks that use raw FP32 throughput. Its higher memory bandwidth and larger 11 GB frame buffer further support its performance in high-resolution texture-heavy workloads.

The GeForce RTX 2060 SUPER, however, is not without merit. Its 91.1% lead in Vulkan performance is a strong indicator of future-proofing. For users who play Vulkan-based games or use applications that leverage that API, the RTX 2060 SUPER will be significantly faster. The 13.3% lead in OpenCL also makes it attractive for certain compute environments. Additionally, the presence of RT cores and tensor cores in the Turing architecture provides hardware support for ray tracing and DLSS, features that the GTX 1080 Ti cannot utilize. However, the benchmark data does not include any ray tracing or DLSS tests, so their impact cannot be quantified here.

Ultimately, the choice depends on which workloads are prioritized. For pure rasterized gaming performance across a broad library of DirectX titles, the GTX 1080 Ti is the clear winner. For users who value Vulkan performance, lower power consumption (175 W versus 250 W), and access to newer feature sets, the RTX 2060 SUPER is the more versatile option despite losing most traditional benchmarks.

Specification Differences

The following specifications differ between the two cards based on the database records:

| Specification | NVIDIA GeForce RTX 2060 SUPER | NVIDIA GeForce GTX 1080 Ti |

| :--- | :--- | :--- |

| Architecture | Turing | Pascal |

| Process Node | 12 nm | 16 nm |

| Transistors | 10,800 million | 11,800 million |

| Die Size | 445 mm² | 471 mm² |

| Transistor Density | 24.3M / mm² | 25.1M / mm² |

| Base Clock | 1470 MHz | 1481 MHz |

| Boost Clock | 1650 MHz | 1582 MHz |

| Memory Clock | 1750 MHz (14 Gbps effective) | 1376 MHz (11 Gbps effective) |

| Memory Size | 8 GB | 11 GB |

| Memory Type | GDDR6 | GDDR5X |

| Memory Bus Width | 256 bit | 352 bit |

| Memory Bandwidth | 448.0 GB/s | 484.4 GB/s |

| Shading Units | 2176 | 3584 |

| TMUs | 136 | 224 |

| ROPs | 64 | 88 |

| RT Cores | 34 | None |

| Tensor Cores | 272 | None |

| Pixel Rate | 105.6 GPixel/s | 139.2 GPixel/s |

| Texture Rate | 224.4 GTexel/s | 354.4 GTexel/s |

| FP32 Performance | 7.181 TFLOPS | 11.34 TFLOPS |

| FP16 Performance | 14.36 TFLOPS (2:1) | 177.2 GFLOPS (1:64) |

| TDP | 175 W | 250 W |

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

| Suggested PSU | 450 W | 600 W |

| Display Outputs | 1x DVI, 1x HDMI 2.0, 2x DisplayPort 1.4a, 1x USB Type-C | 1x HDMI 2.0, 3x DisplayPort 1.4a |

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

| Length | 229 mm (9 inches) | 267 mm (10.5 inches) |

| Width | 35 mm (1.4 inches) | 40 mm (1.6 inches) |

| Release Date | 2019-07-08 | 2017-03-09 |

| Launch MSRP | 399 USD | 699 USD |