AMD Radeon RX 5500 XT vs NVIDIA GeForce GTX 1660 SUPER Comparison

Where Each One Wins

The head-to-head benchmark data is unambiguous: the NVIDIA GeForce GTX 1660 SUPER wins all ten recorded tests against the AMD Radeon RX 5500 XT. There is no test category, whether synthetic 3D rendering, compute workloads, or legacy DirectX paths, where the AMD card takes a lead. The win count stands at 10 for NVIDIA and 0 for AMD.

Looking at the use-case split, the GTX 1660 SUPER dominates in DirectX 11 titles, where it posts a score of 104 versus the RX 5500 XT's 56, a 46.2% advantage. This is the largest delta in the entire comparison and matters for the many games still running on that API. The DirectX 9 gap is also substantial at 29.6%, with scores of 189 versus 133. Legacy game performance is clearly an NVIDIA strength.

For modern workloads, the 3DMark Steel Nomad DX12 test shows the GTX 1660 SUPER at 1278 against 1032 for the AMD card, a 19.2% lead. The newer API does not close the gap. Compute performance, measured by PassMark's GPU Compute test, also favors NVIDIA, though by a smaller margin of 12.4% (5076 versus 4446).

The only close contest is in the 2D graphics test (PassMark G2D), where the GTX 1660 SUPER leads by just 3.9% (805 versus 774). This suggests that in purely 2D desktop or lightweight graphical tasks, the two cards are nearly equivalent. Everywhere else, the NVIDIA card pulls ahead by margins ranging from roughly 10% to nearly half.

Architecture Differences

The two cards come from different architectural generations and process nodes. The AMD Radeon RX 5500 XT uses the Navi 14 chip built on RDNA 1.0 architecture, fabricated on a 7 nm process at TSMC. The NVIDIA GeForce GTX 1660 SUPER uses the TU116 chip with Turing architecture, fabricated on a 12 nm process, also at TSMC. The process node difference is significant: 7 nm versus 12 nm, which explains part of the transistor density gap. The AMD chip packs 6,400 million transistors into a 158 mm² die, yielding 40.5 million transistors per square millimeter. The NVIDIA chip holds 6,600 million transistors on a 284 mm² die, a density of 23.2 million per square millimeter.

Both cards have identical counts of shading units (1408) and texture mapping units (88). The ROP count differs, with the RX 5500 XT at 32 and the GTX 1660 SUPER at 48, a 50% higher count on the NVIDIA side. This contributes to the pixel fill rate difference: 59.04 GPixel/s for AMD versus 85.68 GPixel/s for NVIDIA. Texture fill rates are closer, at 162.4 GTexel/s for AMD and 157.1 GTexel/s for NVIDIA, with the AMD card holding a slight edge here. FP32 compute is also close: 5.196 TFLOPS for AMD versus 5.027 TFLOPS for NVIDIA, a small AMD lead.

Memory configurations differ substantially. The RX 5500 XT has 4 GB of GDDR6 on a 128-bit bus, delivering 224.0 GB/s of bandwidth. The GTX 1660 SUPER has 6 GB of GDDR6 on a 192-bit bus, delivering 336.0 GB/s. Both use the same memory clock of 1750 MHz with 14 Gbps effective transfer rate. The extra 2 GB and 112 GB/s of bandwidth give NVIDIA a clear memory advantage.

The bus interface also differs: the AMD card uses PCIe 4.0 x8, while the NVIDIA card uses PCIe 3.0 x16. Display outputs vary as well, with the RX 5500 XT offering 1x HDMI 2.0b and 3x DisplayPort 1.4a, while the GTX 1660 SUPER provides 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a. Power draw is close, with TDP at 130 W for AMD and 125 W for NVIDIA, both using a single 8-pin connector and a 300 W suggested PSU. The AMD card is shorter at 180 mm versus 229 mm for NVIDIA, which also has listed height and width dimensions.

Head-to-Head Benchmarks

The largest single win for the GTX 1660 SUPER comes in the PassMark DirectX 11 test. The NVIDIA card scores 104 against 56 for the RX 5500 XT, a delta of 46.2%. This is nearly double the performance in that specific API workload. The DirectX 9 test shows a similar pattern, with 189 versus 133, a 29.6% gap. DirectX 10 shows 65 versus 46, a 29.2% difference. DirectX 12 narrows the gap to 20%, with scores of 50 and 40.

In the 3DMark Steel Nomad DX12 test, the GTX 1660 SUPER scores 1278 against 1032, a 19.2% lead. This is a modern, demanding workload and the NVIDIA card still wins comfortably. The Vulkan compute test (Geekbench Vulkan) shows the largest compute gap: 57102 versus 44191, a 22.6% difference. OpenCL performance is closer, with 52490 versus 46965, a 10.5% lead for NVIDIA.

The PassMark G3D test, which aggregates overall 3D graphics performance, shows 12699 for NVIDIA versus 9083 for AMD, a 28.5% advantage. The GPU Compute test shows a smaller gap of 12.4%, with 5076 versus 4446. The G2D test is the closest at 3.9%, with 805 versus 774.

The average benchmark score in the database reflects this overall trend. The RX 5500 XT has an average score of 14692 across all recorded benchmarks, while the GTX 1660 SUPER averages 12986. However, these averages include different benchmark suites and are not directly comparable to the head-to-head results. The percentile rankings place the AMD card at 57th percentile versus 53rd for NVIDIA, but the head-to-head data is the more reliable indicator of relative performance.

FAQ

Q: Which card has higher raw compute performance?

A: The AMD Radeon RX 5500 XT has slightly higher FP32 compute at 5.196 TFLOPS versus 5.027 TFLOPS for the NVIDIA GeForce GTX 1660 SUPER. However, in the PassMark GPU Compute test, the NVIDIA card scores 5076 against 4446, a 12.4% lead.

Q: What is the memory bandwidth difference?

A: The GTX 1660 SUPER has 336.0 GB/s of bandwidth from its 192-bit bus and 6 GB of GDDR6 memory. The RX 5500 XT has 224.0 GB/s from a 128-bit bus and 4 GB of GDDR6. Both run at 14 Gbps effective memory speed.

Q: Which card performs better in DirectX 11 games?

A: The GTX 1660 SUPER is significantly ahead. The PassMark DirectX 11 test shows a score of 104 versus 56, a 46.2% advantage for NVIDIA. This is the largest performance gap in any recorded test.

Q: Are there any tests where the RX 5500 XT wins?

A: No. Across all ten head-to-head benchmarks in the database, the GTX 1660 SUPER wins every single test. The closest result is the PassMark G2D test, where NVIDIA leads by just 3.9%.

Q: What is the transistor density difference?

A: The RX 5500 XT has 40.5 million transistors per square millimeter on its 7 nm process, while the GTX 1660 SUPER has 23.2 million per square millimeter on 12 nm. The AMD chip is smaller at 158 mm² versus 284 mm².

Q: How do the pixel fill rates compare?

A: The GTX 1660 SUPER has a pixel rate of 85.68 GPixel/s, which is 45% higher than the RX 5500 XT's 59.04 GPixel/s. This aligns with the NVIDIA card having 48 ROPs versus 32 on the AMD card.

The Verdict

The data points to a clear conclusion: the NVIDIA GeForce GTX 1660 SUPER outperforms the AMD Radeon RX 5500 XT across every recorded benchmark. The margins vary from a modest 3.9% in 2D graphics to a dominant 46.2% in DirectX 11 workloads. For anyone prioritizing gaming performance, particularly in DirectX 11 titles, the GTX 1660 SUPER is the stronger choice. The 6 GB memory capacity and 336.0 GB/s bandwidth also make it better suited for modern game textures and higher resolutions.

The RX 5500 XT does have some advantages in the specification sheet. It offers higher FP32 compute (5.196 versus 5.027 TFLOPS), a smaller die (158 mm² versus 284 mm²), higher transistor density, and a shorter card length (180 mm versus 229 mm). Its PCIe 4.0 x8 interface is newer than the PCIe 3.0 x16 on the NVIDIA card. These factors may appeal to users with space constraints or those running compute workloads that favor the AMD architecture. The 7 nm process node also suggests better efficiency per transistor, though the TDP is slightly higher at 130 W versus 125 W.

However, in actual benchmark performance, the AMD card does not convert its theoretical advantages into wins. The GTX 1660 SUPER's higher ROP count, larger memory bus, and greater bandwidth translate directly into higher frame rates and better compute scores. The 10-0 record in head-to-head tests leaves little room for interpretation. Users should pick the GTX 1660 SUPER for almost any workload, reserving the RX 5500 XT for cases where its smaller physical size or specific feature set matters more than raw performance.

Specification Differences

| Specification | AMD Radeon RX 5500 XT | NVIDIA GeForce GTX 1660 SUPER |

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

| Architecture | RDNA 1.0 | Turing |

| Process Node | 7 nm | 12 nm |

| Transistors | 6,400 million | 6,600 million |

| Die Size | 158 mm² | 284 mm² |

| Transistor Density | 40.5M / mm² | 23.2M / mm² |

| Base Clock | 1607 MHz | 1530 MHz |

| Boost Clock | 1845 MHz | 1785 MHz |

| Game Clock | 1717 MHz | Not specified |

| Memory Size | 4 GB | 6 GB |

| Memory Bus Width | 128 bit | 192 bit |

| Memory Bandwidth | 224.0 GB/s | 336.0 GB/s |

| ROPs | 32 | 48 |

| Pixel Rate | 59.04 GPixel/s | 85.68 GPixel/s |

| Texture Rate | 162.4 GTexel/s | 157.1 GTexel/s |

| FP32 | 5.196 TFLOPS | 5.027 TFLOPS |

| FP16 | 10.39 TFLOPS (2:1) | 10.05 TFLOPS (2:1) |

| TDP | 130 W | 125 W |

| Bus Interface | PCIe 4.0 x8 | PCIe 3.0 x16 |

| Display Outputs | 1x HDMI 2.0b, 3x DisplayPort 1.4a | 1x DVI, 1x HDMI 2.0, 1x DisplayPort 1.4a |

| Length | 180 mm (7.1 inches) | 229 mm (9 inches) |

| Height | Not specified | 111 mm (4.4 inches) |

| Width | Not specified | 35 mm (1.4 inches) |

| Release Date | 2019-12-11 | 2019-10-28 |

| Launch MSRP | 169 USD | 229 USD |