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

The AMD Radeon RX 5500M and NVIDIA GeForce GTX 1660 SUPER occupy different corners of the GPU market, with the former designed for thin-and-light mobile gaming and the latter as a desktop-oriented card. The benchmark data reveals a stark performance hierarchy, with the NVIDIA card dominating the head-to-head results across every single test, yet the AMD part still holds a slight edge in aggregate benchmark scoring. This creates a curious dynamic where the slower card in direct comparisons appears to have better overall standing among its peers.

Head-to-Head Benchmarks

The head-to-head results are unequivocal. The NVIDIA GeForce GTX 1660 SUPER wins all nine benchmark comparisons, with the AMD Radeon RX 5500M failing to secure a single victory. The largest margin comes in PassMark DirectX 11, where the GTX 1660 SUPER scores 104 against the RX 5500M’s 35, representing a 66.3% advantage. This is a massive gap that suggests the NVIDIA architecture handles legacy DirectX workloads with far greater efficiency.

The Vulkan and OpenCL results follow a similar pattern. In Geekbench Vulkan, the GTX 1660 SUPER posts 57102 versus 35693, a 37.5% delta. Geekbench OpenCL shows 52490 versus 38725, a 26.2% gap. These compute-oriented tests indicate that the NVIDIA card’s higher raw throughput translates directly into API-agnostic performance advantages.

The PassMark suite reveals consistent NVIDIA dominance. DirectX 10 shows a 40% lead (65 vs 39), DirectX 12 shows 44% (50 vs 28), and DirectX 9 shows 47.1% (189 vs 100). The Graphics 3D score is particularly lopsided: 12699 versus 5848, a 53.9% deficit for the AMD card. Even the Graphics 2D test, which often favors efficiency over raw power, shows a 48.6% gap (805 vs 414). GPU compute follows suit with a 54.4% difference (5076 vs 2316).

Interestingly, the average benchmark score tells a different story. The RX 5500M averages 13356 across all tests, while the GTX 1660 SUPER averages 12986. This discrepancy stems from the different benchmark mixes included in each card’s average — the AMD card’s Geekbench Metal score of 50359 likely skews its average upward, while the NVIDIA card lacks that test. The percentiles reflect this: the RX 5500M sits at the 54th percentile of all GPUs, slightly above the GTX 1660 SUPER’s 53rd percentile.

Architecture Differences

The architectural divide between these two parts is fundamental. The AMD Radeon RX 5500M uses the Navi 14 chip built on RDNA 1.0 architecture, manufactured on a 7 nm process at TSMC. It packs 6,400 million transistors into a 158 mm² die, achieving a transistor density of 40.5M per mm². The NVIDIA GeForce GTX 1660 SUPER, by contrast, uses the TU116 chip with Turing architecture on a 12 nm process, also at TSMC. It houses 6,600 million transistors across a much larger 284 mm² die, with a density of just 23.2M per mm².

Clock speeds favor the NVIDIA card. The GTX 1660 SUPER runs at a 1530 MHz base and 1785 MHz boost, while the RX 5500M operates at 1375 MHz base and 1645 MHz boost. Both use 1750 MHz memory with 14 Gbps effective speed, but the memory configurations diverge sharply. The RX 5500M has 4 GB of GDDR6 on a 128-bit bus, yielding 224.0 GB/s bandwidth. The GTX 1660 SUPER offers 6 GB of GDDR6 on a 192-bit bus, producing 336.0 GB/s — exactly 50% more bandwidth.

Shading units and texture mapping units match at 1408 and 88 respectively. The ROP count differs, however: the NVIDIA card has 48 ROPs versus 32 on the AMD part. This explains the pixel rate gap — 85.68 GPixel/s for NVIDIA versus 52.64 GPixel/s for AMD. Texture rates also favor NVIDIA at 157.1 GTexel/s versus 144.8 GTexel/s. FP32 compute is closer: 5.027 TFLOPS for NVIDIA versus 4.632 TFLOPS for AMD, a difference of roughly 8.5%. FP16 performance scales similarly at 10.05 TFLOPS versus 9.265 TFLOPS, both using a 2:1 ratio.

Power and connectivity reveal their intended use cases. The RX 5500M draws 85 W with no power connectors, indicating a mobile design meant to run off the motherboard. The GTX 1660 SUPER consumes 125 W, requires a single 8-pin connector, and comes with a 300 W suggested power supply. The AMD card uses PCIe 4.0 x8, while NVIDIA uses PCIe 3.0 x16. Display outputs also reflect their purposes: the AMD card is "portable device dependent," while the NVIDIA card offers 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a.

Where Each One Wins

The data does not support any benchmark win for the AMD Radeon RX 5500M in direct comparison. The NVIDIA GeForce GTX 1660 SUPER wins every single test. However, the RX 5500M’s higher average score and percentile ranking suggest it performs better relative to its own peer group. Its nearest rivals include the AMD Radeon Pro 555X (0.3% faster), AMD FirePro M6100 (0% difference), and AMD Radeon HD 8950M (0.1% slower). The GTX 1660 SUPER’s nearest rivals include the NVIDIA GeForce RTX 3050 Ti Mobile (0.4% faster), AMD Radeon RX 580 (0.4% slower), and AMD Radeon 740M (0.9% slower).

For real-world use, the GTX 1660 SUPER is the clear choice for desktop gaming, particularly for DirectX 11 workloads where its 66.3% advantage is most pronounced. The RX 5500M, with its 85 W power envelope and lack of external connectors, fits into laptops where thermal and power constraints dominate. Its 4 GB VRAM is sufficient for 1080p gaming at moderate settings, while the 6 GB on the NVIDIA card provides more headroom for modern textures.

The API support is identical for both: DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. Neither card has ray tracing or tensor cores. In compute scenarios, the NVIDIA card’s 54.4% lead in GPU compute makes it better suited for tasks like rendering or machine learning inference, while the AMD card’s efficiency per watt could be advantageous in battery-powered scenarios.

The Verdict

From the benchmark data alone, the NVIDIA GeForce GTX 1660 SUPER is the superior performer in every measurable way. It wins all nine head-to-head comparisons, with margins ranging from 26.2% to 66.3%. The most decisive advantage is in DirectX 11, where the delta reaches 66.3%, indicating a generational leap in legacy API handling. The 53.9% gap in Graphics 3D and 54.4% in GPU compute reinforce this as a comprehensive victory.

The AMD Radeon RX 5500M, however, is not without merit. Its 54th percentile ranking versus the NVIDIA card’s 53rd shows it compares more favorably to its mobile-oriented peers. The 7 nm process gives it a transistor density advantage of 40.5M per mm² versus 23.2M per mm², suggesting better efficiency per square millimeter. The 85 W power draw versus 125 W makes it suitable for systems where the GTX 1660 SUPER would be impractical.

The choice comes down to platform. For a desktop user, the GTX 1660 SUPER is the only rational pick based on performance data alone. For a laptop manufacturer or user prioritizing power efficiency and portability, the RX 5500M offers a compelling mobile solution, even if it sacrifices significant performance. The 4 GB versus 6 GB VRAM difference also matters for future-proofing — the NVIDIA card has 50% more memory.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The AMD Radeon RX 5500M averages 13356, while the NVIDIA GeForce GTX 1660 SUPER averages 12986.

Q: What is the largest performance gap in head-to-head testing?

A: The PassMark DirectX 11 test shows the biggest delta, with the GTX 1660 SUPER scoring 104 versus 35 for the RX 5500M, a 66.3% advantage.

Q: Do both cards support the same APIs?

A: Yes, both support DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4.

Q: How do their memory bandwidths compare?

A: The GTX 1660 SUPER has 336.0 GB/s bandwidth from 6 GB GDDR6 on a 192-bit bus, while the RX 5500M has 224.0 GB/s from 4 GB GDDR6 on a 128-bit bus.

Q: What are the power requirements for each card?

A: The RX 5500M draws 85 W with no power connectors, while the GTX 1660 SUPER draws 125 W and requires a single 8-pin connector with a 300 W suggested power supply.

Q: Which card ranks higher among all GPUs by percentile?

A: The RX 5500M ranks in the 54th percentile, slightly above the GTX 1660 SUPER’s 53rd percentile.

Specification Differences

| Field | AMD Radeon RX 5500M | 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 | 1375 MHz | 1530 MHz |

| Boost Clock | 1645 MHz | 1785 MHz |

| 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 | 52.64 GPixel/s | 85.68 GPixel/s |

| Texture Rate | 144.8 GTexel/s | 157.1 GTexel/s |

| FP32 Performance | 4.632 TFLOPS | 5.027 TFLOPS |

| FP16 Performance | 9.265 TFLOPS (2:1) | 10.05 TFLOPS (2:1) |

| TDP | 85 W | 125 W |

| Slot Width | Not specified | Dual-slot |

| Power Connectors | None | 1x 8-pin |

| Suggested PSU | Not specified | 300 W |

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

| Display Outputs | Portable Device Dependent | 1x DVI, 1x HDMI 2.0, 1x DisplayPort 1.4a |

| Dimensions | Not specified | 229 mm x 111 mm x 35 mm |

| Release Date | 2019-10-06 | 2019-10-28 |

| Predecessor | Polaris Mobile | GeForce 10 |

| Successor | None | GeForce 20 |