NVIDIA GeForce RTX 2080 SUPER vs NVIDIA GeForce RTX 5060 Comparison

The NVIDIA GeForce RTX 5060 is the clear winner in this comparison, taking 8 of 10 head-to-head benchmark victories against the RTX 2080 SUPER, including a dominant 92.8% margin in the 3DMark Steel Nomad DX12 test. The RTX 2080 SUPER retains only two narrow wins in legacy DirectX 10 and DirectX 9 workloads, but the overall data points to a decisive generational shift, with the RTX 5060 delivering higher performance, a smaller die, and dramatically lower power requirements.

Head-to-Head Benchmarks

The most striking result is in the 3DMark Steel Nomad DX12 test, where the RTX 5060 scores 3628 against the RTX 2080 SUPER’s 1882, a 92.8% advantage. This is not a marginal improvement; it represents nearly double the performance in a modern DirectX 12 workload, highlighting how far architecture has advanced since the Turing generation.

In compute-heavy tasks, the RTX 5060 again leads decisively. The PassMark GPU Compute test shows the RTX 5060 at 10899 versus 8290 for the RTX 2080 SUPER, a 31.5% delta. Similarly, in Geekbench OpenCL, the RTX 5060 posts 112787 against 99226, a 13.7% edge. These results indicate that Blackwell 2.0’s execution efficiency translates directly into superior raw compute throughput, despite the RTX 5060 having fewer shading units (3840 vs 3072 is actually more, but the comparison here is about efficiency).

The gap narrows in other synthetic tests. PassMark G3D shows the RTX 5060 at 20891 versus 19490, a 7.2% win. PassMark DirectX 11 favors the RTX 5060 by 21.2% (200 vs 165), while DirectX 12 is closer at 2.7% (77 vs 75). The RTX 5060 also wins PassMark G2D by 25.4% (1154 vs 920), which is notable for desktop and 2D-accelerated workloads. In Geekbench Vulkan, the RTX 5060 edges ahead by only 1.8% (113321 vs 111284), suggesting that Vulkan performance is more evenly matched than DX12 or compute.

The RTX 2080 SUPER’s two wins are narrow and confined to legacy APIs. In PassMark DirectX 10, it scores 140 against 127, a 9.3% advantage. In DirectX 9, it wins 227 to 225, a marginal 0.9% delta. These results suggest the older card retains some strength in older game engines, but the performance gap is small and increasingly irrelevant for modern workloads.

Averaging all benchmarks, the RTX 5060’s average score is 26331, while the RTX 2080 SUPER averages 24170. The RTX 5060’s percentile rank among all GPUs is 72, compared to 69 for the RTX 2080 SUPER. For context, the RTX 5060’s nearest rivals include the AMD Radeon RX 6750 XT (1.2% faster) and the AMD Radeon RX 5700 XT 50th Anniversary (0.8% slower), while the RTX 2080 SUPER sits near the NVIDIA GeForce GTX 780 Ti (0.3% slower) and the AMD Radeon RX 6600 XT (1.1% faster).

FAQ

Q: How much faster is the RTX 5060 in the most demanding modern benchmark?

A: In the 3DMark Steel Nomad DX12 test, the RTX 5060 scores 3628 versus 1882 for the RTX 2080 SUPER, a 92.8% performance advantage.

Q: Does the RTX 2080 SUPER win any benchmarks?

A: Yes, it wins two legacy tests: PassMark DirectX 10 (140 vs 127, a 9.3% lead) and PassMark DirectX 9 (227 vs 225, a 0.9% lead).

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

A: The RTX 5060 leads by 31.5% in PassMark GPU Compute (10899 vs 8290) and by 13.7% in Geekbench OpenCL (112787 vs 99226).

Q: What is the average benchmark score difference?

A: The RTX 5060 averages 26331 points, while the RTX 2080 SUPER averages 24170, a difference of roughly 2161 points in favor of the newer card.

Q: Which card has better Vulkan performance?

A: The RTX 5060 scores 113321 in Geekbench Vulkan, narrowly ahead of the RTX 2080 SUPER’s 111284, a 1.8% lead.

Q: Is the RTX 5060’s lead consistent across all DirectX versions?

A: No. It wins DirectX 11 by 21.2% and DirectX 12 by 2.7%, but loses DirectX 10 by 9.3% and DirectX 9 by 0.9%.

The Verdict

The data is unambiguous: the RTX 5060 is the superior GPU for nearly all workloads. It wins 8 of 10 benchmarks, with the largest margin being a 92.8% blowout in 3DMark Steel Nomad DX12 and the smallest being a 1.8% edge in Geekbench Vulkan. The RTX 2080 SUPER’s only victories are in legacy DirectX 10 and DirectX 9, where it leads by 9.3% and 0.9% respectively — margins that are unlikely to matter for any modern game or application.

For a user prioritizing modern DirectX 12 gaming, compute tasks, or 2D performance, the RTX 5060 is the clear choice. Its average benchmark score of 26331 places it in the 72nd percentile of all GPUs, while the RTX 2080 SUPER sits at 24170 and the 69th percentile. The RTX 2080 SUPER may appeal only to someone running very old software that relies on DirectX 10 or 9, but even then, the performance difference is small. The RTX 5060’s 31.5% lead in GPU compute and 13.7% lead in OpenCL make it the better option for content creation and general-purpose GPU tasks.

Specification Differences

The two cards differ significantly in almost every core specification. The RTX 5060 uses a 5 nm process with 21,900 million transistors on a 181 mm² die, while the RTX 2080 SUPER uses a 12 nm process with 13,600 million transistors on a much larger 545 mm² die. Transistor density tells the story: 121.0M / mm² for the RTX 5060 versus 25.0M / mm² for the RTX 2080 SUPER.

Clock speeds favor the RTX 5060, with a base clock of 2280 MHz and boost of 2497 MHz, compared to 1650 MHz base and 1815 MHz boost on the RTX 2080 SUPER. Memory configuration is more nuanced: both have 8 GB, but the RTX 5060 uses GDDR7 with a 128-bit bus and 448.0 GB/s bandwidth, while the RTX 2080 SUPER uses GDDR6 with a 256-bit bus and 495.9 GB/s bandwidth. The RTX 2080 SUPER actually has higher memory bandwidth, but the RTX 5060 compensates with faster effective memory speed (28 Gbps vs 15.5 Gbps).

Shader configuration differs: the RTX 5060 has 3840 shading units, 120 TMUs, and 48 ROPs, while the RTX 2080 SUPER has 3072 shading units, 192 TMUs, and 64 ROPs. The RTX 2080 SUPER has more TMUs and ROPs, but the RTX 5060 has more shading units. Ray tracing and tensor cores also differ: the RTX 5060 has 30 RT cores and 120 tensor cores, while the RTX 2080 SUPER has 48 RT cores and 384 tensor cores.

Power and connectivity show the generational leap. The RTX 5060 has a TDP of 145 W with a suggested PSU of 300 W and a single 8-pin connector. The RTX 2080 SUPER has a TDP of 250 W, a suggested PSU of 600 W, and requires both a 6-pin and 8-pin connector. The RTX 5060 uses PCIe 5.0 x8, while the RTX 2080 SUPER uses PCIe 3.0 x16. Display outputs differ: the RTX 5060 offers 1x HDMI 2.1b and 3x DisplayPort 2.1b, while the RTX 2080 SUPER offers 1x HDMI 2.0, 3x DisplayPort 1.4a, and 1x USB Type-C. The RTX 5060 is also smaller at 241 mm in length versus 267 mm for the RTX 2080 SUPER.

Architecture Differences

The RTX 5060 is built on the Blackwell 2.0 architecture, using the GB206 chip, while the RTX 2080 SUPER is based on the Turing architecture with the TU104 chip. The process node difference is stark: 5 nm for the RTX 5060 versus 12 nm for the RTX 2080 SUPER, both fabricated by TSMC. This explains the dramatic difference in die size (181 mm² vs 545 mm²) and transistor density (121.0M / mm² vs 25.0M / mm²).

The RTX 5060 achieves 19.18 TFLOPS FP32 performance, while the RTX 2080 SUPER delivers 11.15 TFLOPS FP32. Interestingly, the RTX 2080 SUPER has higher FP16 performance at 22.30 TFLOPS (2:1 ratio), while the RTX 5060 matches FP32 at 19.18 TFLOPS (1:1 ratio). The RTX 5060 has fewer RT cores (30 vs 48) and tensor cores (120 vs 384), yet still wins in modern benchmarks, indicating that architecture efficiency matters more than raw core counts.

The RTX 5060 is an active production card from the GeForce 50-series, released in 2025, while the RTX 2080 SUPER is end-of-life from the GeForce 20-series, released in 2019. The RTX 5060’s predecessor is GeForce 40, and its successor is GeForce 60. The RTX 2080 SUPER’s predecessor is GeForce 10, and its successor is GeForce 30. Both cards support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, meaning API compatibility is identical.

Where Each One Wins

The RTX 5060 wins in every modern workload category. Its 92.8% lead in 3DMark Steel Nomad DX12 makes it the definitive choice for current DirectX 12 games. Its 31.5% advantage in GPU compute and 13.7% lead in OpenCL make it better suited for rendering, machine learning inference, and other compute-heavy tasks. The 25.4% win in PassMark G2D also makes it the better card for desktop environments, video playback, and 2D acceleration.

The RTX 2080 SUPER’s wins are confined to legacy DirectX 10 and DirectX 9, with leads of 9.3% and 0.9% respectively. These APIs are primarily used in older games or specialized enterprise applications. For anyone running modern software, the RTX 5060 is the pick. The RTX 2080 SUPER’s higher memory bandwidth (495.9 GB/s vs 448.0 GB/s) and higher texture rate (348.5 GTexel/s vs 299.6 GTexel/s) do not translate into benchmark victories, suggesting the RTX 5060’s architecture overcomes these deficits through better instruction efficiency and higher clocks.

In terms of system integration, the RTX 5060’s lower TDP (145 W vs 250 W) and simpler power requirements (1x 8-pin vs 1x 6-pin + 1x 8-pin) make it easier to install in a wider range of systems. Its smaller physical footprint (241 mm vs 267 mm length) and PCIe 5.0 x8 interface offer modern connectivity, while the RTX 2080 SUPER’s PCIe 3.0 x16 and USB Type-C output are the only areas where it offers something the RTX 5060 does not. The RTX 5060 also carries a launch MSRP of 299 USD, compared to 699 USD for the RTX 2080 SUPER.