NVIDIA GeForce RTX 2080 vs NVIDIA GeForce RTX 2080 SUPER Comparison

The NVIDIA GeForce RTX 2080 SUPER and the NVIDIA GeForce RTX 2080 are two closely related Turing-based graphics cards that share the same fundamental design goals, but the benchmark data shows a consistent performance gap that favors the newer SUPER variant. The RTX 2080 SUPER wins all ten head-to-head benchmark comparisons, with margins that range from a modest 1.4% to a more substantial 8.7%. This analysis breaks down those results, explores the architectural differences that drive them, and clarifies which card is the better pick based strictly on the measured data.

Head-to-Head Benchmarks

The most decisive victory for the RTX 2080 SUPER comes in the Geekbench OpenCL test, where it scores 99,226 against the RTX 2080's 91,313. That is an 8.7% advantage, the largest delta in the entire comparison set. This test is compute-heavy, and the SUPER's advantage here suggests its additional shading units and higher clock speeds translate directly into raw compute throughput. The Geekbench Vulkan result is closer, with the SUPER scoring 111,284 versus 107,797, a 3.2% lead, indicating that the gap narrows slightly under a graphics API workload but remains firmly in the SUPER's favor.

In the 3DMark Steel Nomad DX12 test, the RTX 2080 SUPER scores 1,882, while the RTX 2080 trails at 1,752. That is a 7.4% difference, the second-largest win for the SUPER. This is a modern, demanding DirectX 12 benchmark, and the SUPER's lead here is significant because it suggests the card will maintain its advantage in current and future gaming titles that utilize DX12 features. The PassMark G3D test, a general gaming and graphics score, also shows a clear separation: the SUPER posts 19,490 versus 18,720, a 4.1% margin.

The remaining wins are smaller but consistent. In PassMark DirectX 11, the SUPER leads 165 to 158, a 4.4% gain. The DirectX 12 PassMark test shows a 4.2% lead (75 vs. 72), and the DirectX 10 test shows a 2.9% lead (140 vs. 136). The oldest API tested, DirectX 9, shows the narrowest gap at 1.8% (227 vs. 223). The PassMark GPU Compute test, which measures non-graphics processing, gives the SUPER a 5.3% edge (8,290 vs. 7,872). Finally, the 2D graphics test (PassMark G2D) is the closest overall, with the SUPER winning 920 to 907, a margin of just 1.4%. This pattern shows that while the SUPER is faster in every scenario, its lead is more pronounced in compute-heavy and modern API workloads, and less so in legacy 2D tasks.

Architecture Differences

Both cards are built on the same TU104 chip using NVIDIA's Turing architecture, manufactured on a 12 nm process at TSMC. They share the identical transistor count of 13,600 million and the same die size of 545 mm², resulting in a transistor density of 25.0M per mm². The fundamental silicon is therefore the same, but NVIDIA has configured it differently for the SUPER variant.

The most important difference is in the compute units. The RTX 2080 SUPER has 3,072 shading units, 192 texture mapping units (TMUs), and 64 ROPs. The RTX 2080 has 2,944 shading units, 184 TMUs, and the same 64 ROPs. This gives the SUPER a 128-shader and 8-TMU advantage. The ray tracing and tensor core counts also scale up: the SUPER has 48 RT cores and 384 tensor cores, while the RTX 2080 has 46 and 368, respectively. These extra units directly explain the performance deltas seen in the benchmarks.

Clock speeds are another differentiating factor. The RTX 2080 SUPER has a base clock of 1650 MHz and a boost clock of 1815 MHz. The RTX 2080 is slower on both counts, with a base of 1515 MHz and a boost of 1710 MHz. That higher boost clock, combined with more shaders, yields a notable increase in theoretical throughput: the SUPER delivers 11.15 TFLOPS of FP32 compute versus 10.07 TFLOPS for the RTX 2080. The FP16 figures are similarly higher for the SUPER at 22.30 TFLOPS versus 20.14 TFLOPS, both at a 2:1 ratio.

Memory is also upgraded on the SUPER. Both cards have 8 GB of GDDR6 on a 256-bit bus, but the SUPER's memory runs at 1937 MHz, translating to 15.5 Gbps effective, while the RTX 2080 runs at 1750 MHz (14 Gbps effective). This yields a bandwidth advantage for the SUPER: 495.9 GB/s versus 448.0 GB/s. This is a 10.7% increase in memory bandwidth, which helps in high-resolution textures and compute tasks that are memory-bound. The pixel rate and texture rate reflect the clock and unit differences: the SUPER hits 116.2 GPixel/s and 348.5 GTexel/s, while the RTX 2080 manages 109.4 GPixel/s and 314.6 GTexel/s.

Power consumption is the one area where the RTX 2080 is the more efficient choice. The SUPER has a TDP of 250 W, while the RTX 2080 is rated at 215 W. The suggested PSU is also higher for the SUPER at 600 W versus 550 W. Both cards use the same power connector configuration (1x 6-pin + 1x 8-pin). The physical dimensions are identical: both are dual-slot cards measuring 267 mm in length, 116 mm in height, and 35 mm in width. They also share the same display outputs (1x HDMI 2.0, 3x DisplayPort 1.4a, 1x USB Type-C), bus interface (PCIe 3.0 x16), and API support (DirectX 12 Ultimate, OpenGL 4.6, Vulkan 1.4).

The Verdict

The data is unambiguous: the NVIDIA GeForce RTX 2080 SUPER is the faster card in every single benchmark comparison. It wins all ten head-to-head tests, with an average benchmark score of 24,170 compared to the RTX 2080's 22,895. That is a difference of 1,275 points, or roughly 5.6%. The SUPER's percentile ranking among all GPUs is 69, one point higher than the RTX 2080's 68. The nearest rivals data confirms that both cards sit in a similar performance tier, but the SUPER is consistently ahead. For example, the SUPER is 0.3% behind the GTX 780 Ti (24,236) and 1.1% behind the RX 6600 XT (24,442), while the RTX 2080 is 0.5% behind the Intel Arc B580 (23,021) and 1.2% behind the RTX 3080 (23,172).

The RTX 2080 SUPER's wins range from a slim 1.4% in 2D to a decisive 8.7% in OpenCL compute. The most meaningful wins for gaming are the 7.4% in 3DMark Steel Nomad and the 4.1% in PassMark G3D. The SUPER's higher bandwidth, more shaders, and faster clocks give it a clear edge that holds across all tested APIs and workloads.

There is no scenario in the data where the RTX 2080 comes out ahead. The only advantage the RTX 2080 holds is a lower power draw of 215 W versus 250 W, which might appeal to users with strict power or thermal limits, but this does not translate into any performance benefit. The verdict is straightforward: for anyone choosing between these two based on benchmark results, the RTX 2080 SUPER is the superior performer.

Specification Differences

The following specifications differ between the two cards. All other listed specifications, including the TU104 chip, 12 nm process, 13,600 million transistors, 545 mm² die size, 8 GB GDDR6 memory, 256-bit bus width, 64 ROPs, dual-slot design, 1x 6-pin + 1x 8-pin connectors, PCIe 3.0 x16 interface, display outputs, APIs, and physical dimensions, are identical.

| Specification | RTX 2080 SUPER | RTX 2080 |

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

| Shading Units | 3072 | 2944 |

| TMUs | 192 | 184 |

| RT Cores | 48 | 46 |

| Tensor Cores | 384 | 368 |

| Base Clock | 1650 MHz | 1515 MHz |

| Boost Clock | 1815 MHz | 1710 MHz |

| Memory Clock | 1937 MHz / 15.5 Gbps effective | 1750 MHz / 14 Gbps effective |

| Memory Bandwidth | 495.9 GB/s | 448.0 GB/s |

| Pixel Rate | 116.2 GPixel/s | 109.4 GPixel/s |

| Texture Rate | 348.5 GTexel/s | 314.6 GTexel/s |

| FP32 Performance | 11.15 TFLOPS | 10.07 TFLOPS |

| FP16 Performance | 22.30 TFLOPS (2:1) | 20.14 TFLOPS (2:1) |

| TDP | 250 W | 215 W |

| Suggested PSU | 600 W | 550 W |

| Release Date | 2019-07-22 | 2018-09-19 |

| Launch MSRP | 699 USD | 699 USD |

FAQ

Q: Which card has a higher average benchmark score?

A: The NVIDIA GeForce RTX 2080 SUPER has a higher average benchmark score of 24,170, compared to 22,895 for the RTX 2080.

Q: How much faster is the RTX 2080 SUPER in the 3DMark Steel Nomad DX12 test?

A: The RTX 2080 SUPER scores 1,882, which is 7.4% higher than the RTX 2080's score of 1,752.

Q: Is there any benchmark where the RTX 2080 wins?

A: No. The RTX 2080 SUPER wins all ten head-to-head benchmark comparisons listed, with the RTX 2080 winning zero.

Q: Do these cards have the same memory amount and bus width?

A: Yes, both cards have 8 GB of GDDR6 memory on a 256-bit bus, but the SUPER has higher bandwidth at 495.9 GB/s versus 448.0 GB/s.

Q: What is the difference in TDP between the two cards?

A: The RTX 2080 SUPER has a TDP of 250 W, while the RTX 2080 has a lower TDP of 215 W.

Q: Which card has a higher boost clock?

A: The RTX 2080 SUPER has a boost clock of 1815 MHz, which is higher than the RTX 2080's boost clock of 1710 MHz.

Where Each One Wins

The RTX 2080 SUPER is the winner in every performance category measured. Its largest margins are in compute workloads, where it leads by 8.7% in Geekbench OpenCL and 5.3% in PassMark GPU Compute. This makes it the stronger choice for users who run GPGPU applications, rendering tasks, or any workload that leverages raw shader throughput. Its 7.4% lead in 3DMark Steel Nomad DX12 and 4.1% lead in PassMark G3D also make it the better option for modern gaming, particularly at higher resolutions or with ray tracing enabled, given its additional RT cores and higher memory bandwidth.

The RTX 2080's only "win" is in power efficiency. With a TDP of 215 W versus the SUPER's 250 W, it draws less power and requires a 550 W PSU instead of 600 W. For users with a smaller power supply or a constrained thermal environment, the RTX 2080 might be easier to accommodate, but this comes at a cost of roughly 4-7% performance in most tests. The RTX 2080 also has a slightly lower launch MSRP of 699 USD, matching the SUPER's launch MSRP of 699 USD. Since the prices are identical and the SUPER is faster in every benchmark, the data supports choosing the RTX 2080 SUPER unless the lower power draw of the RTX 2080 is a critical requirement. The RTX 2080's narrowest defeats are in legacy 2D (1.4%) and DirectX 9 (1.8%) tests, suggesting that in very old or light workloads, the performance difference is negligible, but it is still in the SUPER's favor.