NVIDIA GeForce GTX 1060 5 GB vs NVIDIA GeForce RTX 2080 Ti Comparison

The Verdict

The benchmark data separates these two NVIDIA cards into entirely different performance classes. The RTX 2080 Ti wins all recorded head-to-head tests, with the GTX 1060 5 GB trailing by roughly 74% in both OpenCL and Vulkan workloads. For any user whose priority is raw compute throughput, the RTX 2080 Ti is the clear choice from this dataset.

The GTX 1060 5 GB holds a percentile ranking of 78 among all GPUs in the database, while the RTX 2080 Ti sits at percentile 75. This is a notable inversion: the older, smaller card ranks higher in percentile despite losing decisively in direct comparisons. The explanation lies in the average benchmark scores. The GTX 1060 5 GB averages 33,694 points across its recorded tests, while the RTX 2080 Ti averages 29,783 points. The RTX 2080 Ti's average is dragged down by its inclusion of older DirectX 9, 10, and 11 tests, where it scores far lower than in modern workloads. Users focused on current-generation APIs should weight the head-to-head results more heavily than the aggregate averages.

For the GTX 1060 5 GB, the nearest rivals in the database are the NVIDIA RTX A5000 at 33,622 (0.2% behind), the AMD Radeon RX 7700S at 33,849 (0.5% ahead), the AMD Radeon HD 7950 at 33,951 (0.8% ahead), and the AMD Radeon RX 480 at 33,997 (0.9% ahead). The 1060 sits in a tight cluster where a few percent separates all five cards. For the RTX 2080 Ti, the nearest rivals are the NVIDIA GeForce RTX 5070 Mobile at 29,928 (0.5% ahead), the NVIDIA GeForce RTX 3070 Ti at 29,945 (0.5% ahead), the AMD Radeon RX 6800 at 30,095 (1% ahead), and the AMD FirePro W8000 at 29,211 (2% behind). The 2080 Ti's average score places it slightly below three modern GPUs, but within 1% of each.

The data suggests the RTX 2080 Ti is the pick for anyone running OpenCL or Vulkan workloads, where it outperforms the GTX 1060 5 GB by a factor of roughly four. The GTX 1060 5 GB remains viable only for users who prioritize its higher percentile standing and its position within a closely matched group of mid-range cards.

Architecture Differences

The two GPUs come from different architectural generations and manufacturing processes. The GTX 1060 5 GB uses the GP106 chip built on the Pascal architecture, fabricated by TSMC on a 16 nm process. The RTX 2080 Ti uses the TU102 chip on the Turing architecture, also from TSMC but on a 12 nm process. The transistor counts differ enormously: the GTX 1060 5 GB packs 4,400 million transistors on a 200 mm² die, while the RTX 2080 Ti packs 18,600 million transistors on a 754 mm² die. The transistor density is 22.0 million per mm² for the GTX 1060 5 GB and 24.7 million per mm² for the RTX 2080 Ti, indicating the newer process allows for a modestly tighter packing.

The RTX 2080 Ti introduces hardware features absent from the Pascal-based card. It includes 68 ray tracing cores and 544 tensor cores, neither of which appears on the GTX 1060 5 GB. The DirectX support also differs: the GTX 1060 5 GB supports DirectX 12 (12_1), while the RTX 2080 Ti supports DirectX 12 Ultimate (12_2). Both cards support OpenGL 4.6 and Vulkan 1.4, so API compatibility is otherwise identical.

The memory subsystems reflect the generational leap. The GTX 1060 5 GB uses 5 GB of GDDR5 on a 160-bit bus, with memory clocked at 2002 MHz (8 Gbps effective) and bandwidth of 160.2 GB/s. The RTX 2080 Ti uses 11 GB of GDDR6 on a 352-bit bus, with memory at 1750 MHz (14 Gbps effective) and bandwidth of 616.0 GB/s. The RTX 2080 Ti's memory bandwidth is nearly four times higher, which directly supports its larger compute throughput.

Shader resources scale accordingly. The GTX 1060 5 GB has 1,280 shading units, 80 texture mapping units, and 40 ROPs. The RTX 2080 Ti has 4,352 shading units, 272 TMUs, and 88 ROPs. The pixel rate is 68.36 GPixel/s for the GTX 1060 5 GB versus 136.0 GPixel/s for the RTX 2080 Ti. Texture rate is 136.7 GTexel/s versus 420.2 GTexel/s. FP32 compute is 4.375 TFLOPS for the GTX 1060 5 GB and 13.45 TFLOPS for the RTX 2080 Ti. The FP16 figures also differ sharply: the GTX 1060 5 GB delivers 68.36 GFLOPS at a 1:64 ratio, while the RTX 2080 Ti delivers 26.90 TFLOPS at a 2:1 ratio. The RTX 2080 Ti's FP16 capability is a core architectural difference, enabled by the Turing design.

Clock speeds are the one area where the older card leads. The GTX 1060 5 GB has a base clock of 1506 MHz and a boost clock of 1709 MHz. The RTX 2080 Ti has a base clock of 1350 MHz and a boost clock of 1545 MHz. Despite the lower clocks, the RTX 2080 Ti's larger execution resources produce far higher throughput.

Where Each One Wins

The RTX 2080 Ti wins every recorded head-to-head benchmark. In Geekbench OpenCL, it scores 128,171 against the GTX 1060 5 GB's 33,397, a 73.9% advantage. In Geekbench Vulkan, it scores 132,930 against 33,991, a 74.4% advantage. These are the only two tests shared between the cards in the database, and both favor the RTX 2080 Ti by a wide margin.

Beyond the head-to-head tests, the RTX 2080 Ti has a broader benchmark profile. It records scores in PassMark DirectX 9 (235), DirectX 10 (153), DirectX 11 (190), DirectX 12 (84), G2D (927), G3D (21,548), and GPU compute (10,056), plus a 3DMark Steel Nomad DX12 score of 3,537. The GTX 1060 5 GB has only the two Geekbench entries. The RTX 2080 Ti's G3D score of 21,548 and GPU compute score of 10,056 indicate strong performance in traditional graphics and compute tasks, though no direct GTX 1060 5 GB comparison exists for those tests.

The GTX 1060 5 GB's advantage is positional rather than performance-based. Its percentile rank of 78 exceeds the RTX 2080 Ti's 75, and its average benchmark score of 33,694 beats the RTX 2080 Ti's 29,783. The GTX 1060 5 GB also sits in a competitive cluster with the RTX A5000, RX 7700S, HD 7950, and RX 480, where the largest delta is under 1%. The RTX 2080 Ti's nearest rivals include the RTX 5070 Mobile and RTX 3070 Ti, both of which edge it by 0.5%, and the RX 6800, which leads by 1%. The FirePro W8000 trails by 2%. In terms of raw average score, the GTX 1060 5 GB looks better, but this reflects the limited test set for that card rather than real-world superiority.

For modern API workloads, specifically OpenCL and Vulkan, the RTX 2080 Ti is the only choice from this data. For legacy DirectX 9 through 12 workloads, the RTX 2080 Ti has recorded scores that show it handles those APIs, but the GTX 1060 5 GB has no corresponding entries, so no comparison is possible.

FAQ

Q: Which card has the higher average benchmark score?

A: The GTX 1060 5 GB averages 33,694 points, while the RTX 2080 Ti averages 29,783 points. The GTX 1060 5 GB leads by roughly 13%.

Q: How much faster is the RTX 2080 Ti in OpenCL?

A: The RTX 2080 Ti scores 128,171 in Geekbench OpenCL, compared to 33,397 for the GTX 1060 5 GB, a 73.9% advantage.

Q: Does the GTX 1060 5 GB win any head-to-head benchmark?

A: No. The database records two shared tests, Geekbench OpenCL and Geekbench Vulkan, and the RTX 2080 Ti wins both.

Q: Why does the GTX 1060 5 GB have a higher percentile rank?

A: The GTX 1060 5 GB ranks at percentile 78 versus the RTX 2080 Ti's 75. This is driven by the GTX 1060 5 GB's higher average score across its limited set of two benchmarks, both of which are modern API tests.

Q: What is the memory bandwidth difference?

A: The GTX 1060 5 GB has 160.2 GB/s of bandwidth from 5 GB of GDDR5 on a 160-bit bus. The RTX 2080 Ti has 616.0 GB/s from 11 GB of GDDR6 on a 352-bit bus.

Q: Do both cards support the same DirectX version?

A: No. The GTX 1060 5 GB supports DirectX 12 (12_1), while the RTX 2080 Ti supports DirectX 12 Ultimate (12_2). Both support OpenGL 4.6 and Vulkan 1.4.

Head-to-Head Benchmarks

The shared benchmark suite between these two cards consists of exactly two tests: Geekbench OpenCL and Geekbench Vulkan. Both are compute-oriented workloads that stress shader throughput and memory bandwidth, which explains the RTX 2080 Ti's dominance.

In Geekbench OpenCL, the RTX 2080 Ti scores 128,171 against the GTX 1060 5 GB's 33,397. The delta is 73.9% in favor of the RTX 2080 Ti. To put this in context, the RTX 2080 Ti's score is roughly 3.8 times higher. This aligns with the FP32 compute figures: the RTX 2080 Ti delivers 13.45 TFLOPS versus 4.375 TFLOPS for the GTX 1060 5 GB, a 3.1 times difference. The memory bandwidth gap is even larger, 616.0 GB/s versus 160.2 GB/s, which is 3.8 times higher and matches the OpenCL scaling almost exactly. The RTX 2080 Ti's 4,352 shading units compared to 1,280 also contribute, a 3.4 times increase. The combination of more shaders, higher bandwidth, and the Turing architecture's FP16 capabilities at 26.90 TFLOPS (2:1 ratio) explains the measured result.

In Geekbench Vulkan, the RTX 2080 Ti scores 132,930 against the GTX 1060 5 GB's 33,991, a 74.4% advantage. The RTX 2080 Ti's Vulkan score is slightly higher than its OpenCL score, while the GTX 1060 5 GB's Vulkan score is also slightly higher than its OpenCL score. Both cards improve by a small margin when moving from OpenCL to Vulkan, but the proportional gap remains nearly identical, 73.9% versus 74.4%. This consistency suggests the performance difference is structural rather than API-specific.

The RTX 2080 Ti's other recorded benchmarks provide additional context, though no GTX 1060 5 GB scores exist for direct comparison. Its PassMark G3D score is 21,548, and its GPU compute score is 10,056. The DirectX 9 score of 235, DirectX 10 score of 153, DirectX 11 score of 190, and DirectX 12 score of 84 show expected scaling across API generations. The G2D score of 927 reflects 2D workload performance. The 3DMark Steel Nomad DX12 score of 3,537 is the only modern gaming-oriented test in the RTX 2080 Ti's profile. None of these have corresponding GTX 1060 5 GB entries, so the head-to-head comparison necessarily rests on the two Geekbench tests.

The wins tally is decisive: the RTX 2080 Ti records 2 wins and the GTX 1060 5 GB records 0 wins in shared benchmarks.

Specification Differences

The two cards differ across nearly every specification category. The process node moves from 16 nm on the GTX 1060 5 GB to 12 nm on the RTX 2080 Ti. Transistor count rises from 4,400 million to 18,600 million. Die size grows from 200 mm² to 754 mm². Transistor density increases from 22.0M per mm² to 24.7M per mm².

The GTX 1060 5 GB has a base clock of 1506 MHz and a boost clock of 1709 MHz. The RTX 2080 Ti has a base clock of 1350 MHz and a boost clock of 1545 MHz. Memory clock is 2002 MHz (8 Gbps effective) for the GTX 1060 5 GB versus 1750 MHz (14 Gbps effective) for the RTX 2080 Ti.

Memory specifications diverge completely. The GTX 1060 5 GB uses 5 GB of GDDR5 on a 160-bit bus with 160.2 GB/s bandwidth. The RTX 2080 Ti uses 11 GB of GDDR6 on a 352-bit bus with 616.0 GB/s bandwidth.

Compute resources scale dramatically. Shading units go from 1,280 to 4,352. TMUs go from 80 to 272. ROPs go from 40 to 88. The RTX 2080 Ti adds 68 RT cores and 544 tensor cores, which the GTX 1060 5 GB lacks entirely.

Throughput figures follow the resource scaling. Pixel rate is 68.36 GPixel/s for the GTX 1060 5 GB and 136.0 GPixel/s for the RTX 2080 Ti. Texture rate is 136.7 GTexel/s versus 420.2 GTexel/s. FP32 is 4.375 TFLOPS versus 13.45 TFLOPS. FP16 is 68.36 GFLOPS (1:64) versus 26.90 TFLOPS (2:1).

Power and cooling requirements differ substantially. The GTX 1060 5 GB has a TDP of 120 W, uses a single 6-pin power connector, and recommends a 300 W PSU. The RTX 2080 Ti has a TDP of 250 W, uses dual 8-pin connectors, and recommends a 600 W PSU. Both are dual-slot cards. The GTX 1060 5 GB is 250 mm (9.8 inches) long. The RTX 2080 Ti is 267 mm (10.5 inches) long, 116 mm (4.6 inches) high, and 35 mm (1.4 inches) wide.

Display outputs also differ. The GTX 1060 5 GB offers 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.4a. The RTX 2080 Ti offers 1x HDMI 2.0, 3x DisplayPort 1.4a, and 1x USB Type-C. Both use PCIe 3.0 x16. DirectX support is 12 (12_1) for the GTX 1060 5 GB and 12 Ultimate (12_2) for the RTX 2080 Ti. OpenGL 4.6 and Vulkan 1.4 are shared. The RTX 2080 Ti has a recorded launch MSRP of 999 USD; the GTX 1060 5 GB has no recorded launch MSRP in the database.