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

Head-to-Head Benchmarks

The recorded data shows a decisive sweep in direct comparisons. The NVIDIA GeForce GTX 1660 SUPER wins all nine head-to-head benchmark matchups against the AMD Radeon Pro 5500M, with no wins recorded for the AMD part. The margins are substantial across every test category, from legacy DirectX workloads to modern compute APIs.

The largest single victory comes in the PassMark DirectX 11 test, where the GTX 1660 SUPER scores 104 against the Radeon Pro 5500M's 42, a delta of 147.6%. That is more than double the AMD result in a workload that remains relevant for a wide range of Windows applications. Similarly, the PassMark DirectX 9 test shows the NVIDIA card at 189 versus 96 for AMD, a 96.9% advantage. These two results indicate that the GTX 1660 SUPER carries significantly more headroom in older API paths, which can matter for legacy software compatibility and lighter titles.

In the PassMark DirectX 12 test, the NVIDIA card scores 50 against 29, a 72.4% lead. The DirectX 10 test shows 65 versus 36, an 80.6% margin. Across the entire PassMark DirectX suite, the GTX 1660 SUPER maintains a consistent edge that ranges from roughly 72% to 148%. The pattern is clear: regardless of the DirectX feature level, the NVIDIA architecture delivers markedly higher frame throughput in these synthetic measurements.

The compute-oriented results follow the same trend. In Geekbench OpenCL, the GTX 1660 SUPER scores 52490 versus 31088 for the Radeon Pro 5500M, a 68.8% difference. The Geekbench Vulkan test shows 57102 versus 35134, a 62.5% margin. PassMark GPU Compute adds another data point: 5076 versus 3240, a 56.7% lead. These compute benchmarks suggest that the NVIDIA card offers substantially better raw throughput for OpenCL and Vulkan workloads, which can influence productivity applications and certain game engines.

The overall graphics score in PassMark G3D shows the GTX 1660 SUPER at 12699 versus 6732, a 88.6% advantage. That nearly doubles the AMD score in a broad rasterization test. The 2D test is closer in relative terms, with 805 versus 648, a 24.2% margin, but the NVIDIA card still leads. Notably, the AMD Radeon Pro 5500M does have a Geekbench Metal score of 38235, a test that the GTX 1660 SUPER does not appear in the direct comparison for, and that result is not part of the head-to-head tally.

The average benchmark scores reinforce the gap. The GTX 1660 SUPER averages 12986 across its recorded tests, while the Radeon Pro 5500M averages 11528. That places the NVIDIA card at the 53rd percentile among all GPUs in the database, versus the 51st percentile for the AMD part. The nearest rival data puts the GTX 1660 SUPER within 0.4% of the GeForce RTX 3050 Ti Mobile and the Radeon RX 580, and 0.9% ahead of the Radeon 740M. The Radeon Pro 5500M, meanwhile, sits 1.3% behind the GeForce GTX 1660 (non-SUPER) and 2.4% ahead of the GeForce GTX 780M, with the Radeon RX 7800 XT 0.8% ahead of it.

Architecture Differences

The two GPUs come from different architectural generations and are built on different process nodes. The NVIDIA GeForce GTX 1660 SUPER uses the TU116 chip based on the Turing architecture, fabricated by TSMC on a 12 nm process. The AMD Radeon Pro 5500M uses the Navi 14 chip based on RDNA 1.0, also fabricated by TSMC but on a 7 nm node. The smaller process gives AMD a transistor density advantage: the Navi 14 die packs 40.5 million transistors per square millimeter versus 23.2M for TU116. However, the NVIDIA chip has more total transistors at 6,600 million versus 6,400 million, and a larger die at 284 mm² versus 158 mm².

The core configurations differ in ways that explain some of the performance gap. The GTX 1660 SUPER contains 1408 shading units, 88 texture mapping units, and 48 render output units. The Radeon Pro 5500M has 1536 shading units, 96 TMUs, and only 32 ROPs. Despite having more shaders and TMUs, the AMD card delivers lower pixel throughput: 46.40 GPixel/s versus 85.68 GPixel/s for the NVIDIA card. The texture rates are closer, with 139.2 GTexel/s for AMD versus 157.1 GTexel/s for NVIDIA. The FP32 compute figures show 5.027 TFLOPS for the GTX 1660 SUPER versus 4.454 TFLOPS for the Radeon Pro 5500M, and both cards offer FP16 at a 2:1 ratio, 10.05 TFLOPS versus 8.909 TFLOPS.

Memory subsystems also diverge. The GTX 1660 SUPER has 6 GB of GDDR6 on a 192-bit bus, delivering 336.0 GB/s of bandwidth with a 1750 MHz memory clock and 14 Gbps effective data rate. The Radeon Pro 5500M has 8 GB of GDDR6 on a 128-bit bus, delivering 192.0 GB/s with a 1500 MHz memory clock and 12 Gbps effective data rate. The NVIDIA card offers 75% more bandwidth, which is a significant factor in high-resolution and texture-heavy workloads. The AMD card counters with 2 GB more capacity, which can help in applications that exceed 6 GB of video memory usage.

Clock speeds favor NVIDIA as well. The GTX 1660 SUPER has a base clock of 1530 MHz and a boost clock of 1785 MHz. The Radeon Pro 5500M runs at 1000 MHz base and 1450 MHz boost. The power profiles differ: the NVIDIA card draws 125 W with a single 8-pin power connector and a suggested PSU of 300 W, while the AMD card is rated at 85 W with no power connectors, reflecting its mobile-oriented design for Mac systems. The NVIDIA card is dual-slot and measures 229 mm in length, 111 mm in height, and 35 mm in width, while the AMD card has no recorded dimensions, slot width, or power connector data, as it is a mobile part with display outputs described as "Portable Device Dependent."

Both cards support DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, and neither has ray tracing cores or tensor cores. The NVIDIA card uses a PCIe 3.0 x16 interface, while the AMD card uses PCIe 4.0 x8. The GTX 1660 SUPER outputs include 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a, whereas the AMD card's outputs depend on the portable device it is integrated into.

FAQ

Q: Which GPU wins more head-to-head benchmarks?

A: The NVIDIA GeForce GTX 1660 SUPER wins all 9 recorded head-to-head benchmark matchups against the AMD Radeon Pro 5500M, with the AMD card recording 0 wins.

Q: What is the biggest performance gap between the two cards?

A: The largest margin is in the PassMark DirectX 11 test, where the GTX 1660 SUPER scores 104 versus 42 for the Radeon Pro 5500M, a 147.6% difference.

Q: Does the Radeon Pro 5500M have any memory capacity advantage?

A: Yes, the Radeon Pro 5500M offers 8 GB of GDDR6 memory, while the GTX 1660 SUPER has 6 GB. However, the GTX 1660 SUPER has a 192-bit bus and 336.0 GB/s bandwidth versus the AMD card's 128-bit bus and 192.0 GB/s bandwidth.

Q: How do the average benchmark scores compare?

A: The GTX 1660 SUPER averages 12986 across its recorded tests, while the Radeon Pro 5500M averages 11528. The NVIDIA card sits at the 53rd percentile among all GPUs, the AMD card at the 51st percentile.

Q: Are both cards based on the same process node?

A: No. Both are fabricated by TSMC, but the GTX 1660 SUPER uses a 12 nm process, while the Radeon Pro 5500M uses a 7 nm process. The AMD chip has a higher transistor density of 40.5M per mm² versus 23.2M for NVIDIA.

Q: What API features do both cards share?

A: Both support DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. Neither card includes ray tracing cores or tensor cores.

Specification Differences

The two cards differ in nearly every core specification. The GTX 1660 SUPER uses the TU116 chip on a 12 nm process with 6,600 million transistors and a 284 mm² die. The Radeon Pro 5500M uses the Navi 14 chip on a 7 nm process with 6,400 million transistors and a 158 mm² die. Transistor density is 23.2M per mm² for NVIDIA versus 40.5M per mm² for AMD.

Clock speeds: the GTX 1660 SUPER runs at 1530 MHz base and 1785 MHz boost. The Radeon Pro 5500M runs at 1000 MHz base and 1450 MHz boost. Memory clocks are 1750 MHz (14 Gbps effective) for NVIDIA versus 1500 MHz (12 Gbps effective) for AMD. Memory configuration: 6 GB GDDR6 on a 192-bit bus with 336.0 GB/s bandwidth for NVIDIA, versus 8 GB GDDR6 on a 128-bit bus with 192.0 GB/s bandwidth for AMD.

Core counts: the GTX 1660 SUPER has 1408 shading units, 88 TMUs, and 48 ROPs. The Radeon Pro 5500M has 1536 shading units, 96 TMUs, and 32 ROPs. Pixel rates are 85.68 GPixel/s versus 46.40 GPixel/s. Texture rates are 157.1 GTexel/s versus 139.2 GTexel/s. FP32 compute is 5.027 TFLOPS versus 4.454 TFLOPS. FP16 is 10.05 TFLOPS versus 8.909 TFLOPS, both at a 2:1 ratio.

Power and physical specifications: the GTX 1660 SUPER is rated at 125 W TDP, is dual-slot, uses a single 8-pin power connector, and has a suggested PSU of 300 W. The Radeon Pro 5500M is rated at 85 W TDP, has no power connectors, and no suggested PSU or slot width is recorded. The NVIDIA card measures 229 mm by 111 mm by 35 mm; the AMD card has no recorded dimensions. Bus interface: PCIe 3.0 x16 for NVIDIA versus PCIe 4.0 x8 for AMD. Display outputs: 1x DVI, 1x HDMI 2.0, 1x DisplayPort 1.4a for NVIDIA, versus "Portable Device Dependent" for AMD.

Release timing: the GTX 1660 SUPER was released on 2019-10-28, and the Radeon Pro 5500M on 2019-11-12. The GTX 1660 SUPER has a recorded launch MSRP of 229 USD. The AMD card has no launch MSRP recorded. The GTX 1660 SUPER lists a predecessor of GeForce 10 and a successor of GeForce 20; the AMD card lists neither. Both are end-of-life products.

The Verdict

The benchmark data points to a clear winner for most use cases. The NVIDIA GeForce GTX 1660 SUPER outperforms the AMD Radeon Pro 5500M in every single head-to-head test, with margins ranging from 24.2% in PassMark G2D to 147.6% in PassMark DirectX 11. The NVIDIA card also holds advantages in compute workloads, with 68.8% higher Geekbench OpenCL scores and 62.5% higher Geekbench Vulkan scores. Its average benchmark score of 12986 is 12.6% higher than the AMD card's 11528 average.

The GTX 1660 SUPER is the better choice for users who prioritize raw performance, higher memory bandwidth, and broader API coverage across DirectX and compute workloads. Its 336.0 GB/s bandwidth, 5.027 TFLOPS FP32, and 85.68 GPixel/s pixel rate give it a clear edge in synthetic and likely real-world rendering tasks. The Radeon Pro 5500M does offer 8 GB of memory versus 6 GB, which could be relevant for workloads that require more capacity, and its 85 W TDP makes it a lower-power part, but the recorded performance data shows it trailing substantially in every direct comparison.

The Radeon Pro 5500M is a mobile-focused part designed for portable Mac systems, with no power connectors, no recorded dimensions, and display outputs dependent on the host device. That positioning explains its lower power draw and smaller die, but it does not compensate for the performance deficit in the database measurements. The GTX 1660 SUPER is end-of-life, as is the Radeon Pro 5500M, so neither is a future-proof investment, but among these two, the NVIDIA card is the stronger performer by a wide margin. Users who need the extra 2 GB of memory or the lower power envelope might consider the AMD part, but the data shows the GTX 1660 SUPER is the faster GPU in every benchmark where both were tested.