NVIDIA GeForce GTX 1080 Ti vs NVIDIA GeForce RTX 2060 Comparison

The NVIDIA GeForce GTX 1080 Ti and the NVIDIA GeForce RTX 2060 represent two distinct moments in NVIDIA's lineup, one a flagship from the Pascal era and the other a mid-range entry from the Turing generation. The benchmark data shows a clear overall winner in raw performance, but the story becomes more nuanced when considering modern API support and specific workload characteristics. The GTX 1080 Ti wins 9 out of 10 head-to-head comparisons, yet the RTX 2060 secures a significant victory in Vulkan compute, hinting at architectural shifts that go beyond simple frame rates.

Where Each One Wins

The GTX 1080 Ti is the undisputed champion of legacy and traditional rasterization workloads. Its dominance is most pronounced in compute-heavy DirectX tests, where it leads the RTX 2060 by 75.5% in Passmark GPU Compute and 79.6% in 3DMark Steel Nomad DX12. It also holds substantial advantages in DirectX 11 (37.3% ahead) and DirectX 10 (20.4% ahead), making it the superior choice for older game engines and productivity tasks that rely on these APIs. The 1080 Ti even outperforms in 2D tasks, with a 26% lead in Passmark G2D, suggesting its memory subsystem and overall bandwidth provide benefits beyond just 3D rendering.

The RTX 2060’s single win is a decisive one in Geekbench Vulkan, where it scores 65,846 against the 1080 Ti’s 40,511, a 38.5% advantage. This is not a marginal victory but a substantial reversal of the overall trend. This indicates that the Turing architecture’s Vulkan implementation is significantly more efficient, likely benefiting from newer driver optimizations or hardware-level scheduling improvements. For users running modern Vulkan-based games or compute applications, the RTX 2060 could offer a smoother experience despite its lower raw specs. The data suggests that while the 1080 Ti is a brute-force performer, the 2060 is more refined in specific, modern low-level API scenarios.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The GTX 1080 Ti has an average benchmark score of 15,548, which is 1.7% higher than the RTX 2060’s 15,290. This places both cards in the 58th percentile of all GPUs.

Q: How large is the performance gap in DirectX 12?

A: In Passmark DirectX 12, the GTX 1080 Ti scores 66 compared to the RTX 2060’s 53, giving the 1080 Ti a 24.5% lead. However, in the more demanding 3DMark Steel Nomad DX12 test, the lead expands dramatically to 79.6%, with scores of 2,231 versus 1,242.

Q: Does the RTX 2060 win any benchmark?

A: Yes, the RTX 2060 wins Geekbench Vulkan with a score of 65,846, beating the GTX 1080 Ti’s 40,511 by 38.5%. This is the only head-to-head test the RTX 2060 wins.

Q: What is the difference in memory bandwidth?

A: The GTX 1080 Ti has a memory bandwidth of 484.4 GB/s, which is significantly higher than the RTX 2060’s 336.0 GB/s. This is partly due to the 1080 Ti’s wider 352-bit bus compared to the 2060’s 192-bit bus.

Q: Are both cards the same physical size?

A: No, the GTX 1080 Ti is longer at 267 mm (10.5 inches) and wider at 40 mm (1.6 inches), while the RTX 2060 is 229 mm (9 inches) long and 35 mm (1.4 inches) wide. Both have a similar height of around 112-113 mm.

Head-to-Head Benchmarks

The largest single victory for the GTX 1080 Ti comes in 3DMark Steel Nomad DX12, where it scores 2,231 versus the RTX 2060’s 1,242, a massive 79.6% delta. This test appears to be highly sensitive to the 1080 Ti’s raw compute resources, which include 3,584 shading units and 11.34 TFLOPS of FP32 performance, compared to the 2060’s 1,920 shading units and 6.451 TFLOPS. The gap in Passmark GPU Compute is nearly as stark, with the 1080 Ti scoring 9,632 against 5,488, a 75.5% lead. These results paint a picture of a card that simply has more physical throughput to throw at parallel workloads.

In DirectX 11, the 1080 Ti again shows its strength, scoring 151 versus 110, a 37.3% advantage. This is a common API for many popular games, so the 1080 Ti would likely provide a more consistent high-refresh-rate experience in those titles. The Passmark G3D test shows a 31.8% lead for the 1080 Ti (18,600 vs 14,111), which aligns with its overall rasterization dominance. Even in older APIs like DirectX 9, the 1080 Ti leads by 21.6% (231 vs 190), confirming that its architectural muscle translates across generations of software.

The RTX 2060’s Vulkan win, however, is not a small margin. Its score of 65,846 dwarfs the 1080 Ti’s 40,511, representing a 38.5% swing in the opposite direction. This is a significant outlier in the data, suggesting that the RTX 2060’s Turing architecture is not just a scaled-down version of Pascal but has fundamental improvements in how it handles Vulkan’s explicit multi-threading and command buffer management. For applications that leverage Vulkan’s low overhead, the RTX 2060 could deliver a snappier and more efficient experience, even if its peak frame rates in other APIs are lower.

Specification Differences

The two cards differ significantly in their core configurations. The GTX 1080 Ti features 3,584 shading units, 224 texture mapping units, and 88 ROPs, while the RTX 2060 has 1,920 shading units, 120 TMUs, and 48 ROPs. This explains the 1080 Ti’s higher pixel rate of 139.2 GPixel/s versus the 2060’s 80.64 GPixel/s, and its texture rate of 354.4 GTexel/s versus 201.6 GTexel/s. The 1080 Ti also has a higher base clock of 1,481 MHz and a boost clock of 1,582 MHz, compared to the 2060’s 1,365 MHz base and 1,680 MHz boost, meaning the 2060 boosts higher but starts lower.

Memory is another major differentiator. The 1080 Ti uses 11 GB of GDDR5X on a 352-bit bus, delivering 484.4 GB/s of bandwidth. The RTX 2060 uses 6 GB of GDDR6 on a 192-bit bus, providing 336.0 GB/s. While the 2060’s GDDR6 is faster per pin (14 Gbps effective versus 11 Gbps), the 1080 Ti’s wider bus gives it a substantial bandwidth advantage. The 1080 Ti also has higher power requirements, with a 250 W TDP and a suggested 600 W PSU, while the 2060 is more efficient at 160 W and a 450 W PSU suggestion.

Architecture Differences

The architectural divide is stark. The GTX 1080 Ti is built on the Pascal architecture using the GP102 chip, fabricated on a 16 nm process at TSMC. It has 11,800 million transistors on a 471 mm² die. The RTX 2060 uses the Turing architecture with the TU106 chip, on a 12 nm process, also at TSMC, with 10,800 million transistors on a 445 mm² die. This means the 1080 Ti is physically larger and has more transistors, but the 2060 is denser and more modern.

The most critical architectural difference is the RTX 2060’s inclusion of 30 RT cores and 240 tensor cores, which are entirely absent from the GTX 1080 Ti. These enable hardware-accelerated ray tracing and AI-based features like DLSS. While no ray tracing benchmarks are in the data, the presence of these cores fundamentally changes the feature set. The RTX 2060 also supports DirectX 12 Ultimate (12_2), while the 1080 Ti is limited to DirectX 12 (12_1). The 2060’s FP16 performance is also vastly different, with 12.90 TFLOPS at a 2:1 ratio, versus the 1080 Ti’s 177.2 GFLOPS at a 1:64 ratio, indicating that the 2060 is far more capable for mixed-precision workloads.

The Verdict

The data clearly indicates that the GTX 1080 Ti is the superior card for raw performance in almost every benchmark category. It wins 9 out of 10 head-to-head tests, with leads ranging from 4.5% in OpenCL to 79.6% in 3DMark Steel Nomad. For users prioritizing maximum frame rates in traditional DirectX games, heavy compute tasks, or any workload that benefits from massive memory bandwidth and shading power, the 1080 Ti is the obvious choice. Its 11 GB of VRAM and 484.4 GB/s bandwidth also make it more future-proof for high-resolution texture loads.

The RTX 2060, despite its losses, is not without merit. Its 38.5% victory in Geekbench Vulkan suggests that for a growing number of modern games and applications using Vulkan, it could offer a competitive or even superior experience. Furthermore, its architecture includes RT and tensor cores, enabling features that the 1080 Ti simply cannot perform. The RTX 2060 also supports DirectX 12 Ultimate, a newer API version. For users who prioritize these modern features, lower power consumption (160 W vs 250 W), and a smaller physical footprint, the RTX 2060 is the more forward-looking option, even if its raw numbers are lower in most legacy tests. The choice ultimately depends on whether the user values peak legacy performance or modern API efficiency and feature support.