AMD Radeon Pro 560X vs NVIDIA GeForce GTX 1660 SUPER Comparison

The Verdict

The database comparison between the AMD Radeon Pro 560X and the NVIDIA GeForce GTX 1660 SUPER is decisively one-sided. Across the two shared benchmark tests, the GTX 1660 SUPER wins both, and the margins are enormous. In Geekbench OpenCL, the NVIDIA card scores 52,490 against 9,663 for the AMD part, a gap of 81.6 percent. In Geekbench Vulkan, the NVIDIA card posts 57,102 versus 16,819, a 70.5 percent deficit for the AMD chip. There is no workload in the recorded data where the Radeon Pro 560X comes out ahead.

Who should pick which? The GTX 1660 SUPER is the clear choice for any application that relies on OpenCL or Vulkan acceleration, which covers most modern content creation, rendering, and gaming workloads. The Radeon Pro 560X, however, has one defining trait: it is an integrated GPU (IGP) with no power connectors and a 75 W TDP, designed for portable devices. The GTX 1660 SUPER is a dual-slot, 125 W card requiring a 300 W power supply and a single 8-pin connector, with a 229 mm length. So the Radeon Pro 560X is the only option for ultra-thin laptops or Mac systems where discrete card installation is impossible. If you have the chassis and power budget for the NVIDIA card, the data shows no reason to choose the AMD part. If you are constrained to an IGP form factor, the Radeon Pro 560X is what the database records.

Architecture Differences

The two GPUs come from different process nodes, foundries, and architectural generations. The AMD Radeon Pro 560X uses the Polaris 21 chip on a 14 nm process at GlobalFoundries, built on GCN 4.0 architecture. It integrates 3,000 million transistors on a 123 mm² die, giving a transistor density of 24.4 million per square millimeter. The NVIDIA GeForce GTX 1660 SUPER uses the TU116 chip on a 12 nm process at TSMC, based on Turing architecture. It packs 6,600 million transistors on a 284 mm² die, with a density of 23.2 million per square millimeter. The NVIDIA chip has more than twice the transistor count but a slightly lower density due to the larger die.

The execution resources differ substantially. The Radeon Pro 560X has 1,024 shading units, 64 texture mapping units, and 16 ROPs. The GTX 1660 SUPER has 1,408 shading units, 88 TMUs, and 48 ROPs. That translates to a pixel rate of 16.06 GPixel/s and a texture rate of 64.26 GTexel/s for the AMD card, versus 85.68 GPixel/s and 157.1 GTexel/s for the NVIDIA card. In raw FP32 compute, the NVIDIA part delivers 5.027 TFLOPS, while the AMD part delivers 2.056 TFLOPS. The GTX 1660 SUPER also has a notable FP16 advantage: it reaches 10.05 TFLOPS at a 2:1 ratio, whereas the Radeon Pro 560X only achieves 2.056 TFLOPS with a 1:1 ratio, meaning no extra throughput for half-precision work.

Memory configurations are also far apart. The AMD card has 4 GB of GDDR5 on a 128-bit bus, yielding 94.08 GB/s of bandwidth. The NVIDIA card has 6 GB of GDDR6 on a 192-bit bus, delivering 336.0 GB/s. The memory clock on the NVIDIA part is 1750 MHz with 14 Gbps effective, while the AMD part runs at 1470 MHz with 5.9 Gbps effective. The NVIDIA card also has a wider bus interface: PCIe 3.0 x16 versus PCIe 3.0 x8 on the AMD part.

Feature support differs in the API stack. The Radeon Pro 560X supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. The GTX 1660 SUPER supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The NVIDIA card has a higher DirectX feature level and a newer Vulkan version. Neither GPU has ray tracing cores or tensor cores, so those features are absent from both. The Radeon Pro 560X has no base or boost clock listed in the database, while the GTX 1660 SUPER runs at 1530 MHz base and 1785 MHz boost.

Where Each One Wins

The GTX 1660 SUPER wins in every benchmark category recorded in the database. In Geekbench OpenCL, the NVIDIA card scores 52,490, which is 81.6 percent higher than the Radeon Pro 560X's 9,663. In Geekbench Vulkan, the NVIDIA card scores 57,102, which is 70.5 percent higher than the AMD card's 16,819. Beyond those head-to-head tests, the GTX 1660 SUPER has additional benchmark entries that the AMD card lacks entirely. It scores 12,699 in Passmark G3D, 5,076 in Passmark GPU Compute, 805 in Passmark G2D, and 189 in Passmark DirectX 9. It also posts 104 in Passmark DirectX 11, 65 in Passmark DirectX 10, and 50 in Passmark DirectX 12. The Radeon Pro 560X has no entries in any Passmark tests, so those numbers belong exclusively to the NVIDIA card.

The Radeon Pro 560X does have a meaningful advantage in one dimension: form factor and power. It is an integrated GPU with no power connectors and a 75 W TDP, which the database classifies as "IGP" slot width. The GTX 1660 SUPER is a dual-slot card measuring 229 mm in length, 111 mm in height, and 35 mm in width, with a 125 W TDP and a single 8-pin power connector. The AMD part is also listed as "Portable Device Dependent" for display outputs, meaning it is built into systems that do not support discrete graphics. The NVIDIA card offers 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a. So the Radeon Pro 560X wins only in the niche of mobile, integrated designs where a discrete card cannot physically fit.

In terms of production status, both are end-of-life. The Radeon Pro 560X was released on 2018-07-15, while the GTX 1660 SUPER was released on 2019-10-28. The GTX 1660 SUPER has a listed launch MSRP of 229 USD, which can be stated once as reference. The AMD card has no launch MSRP in the database.

FAQ

Q: Which GPU has higher raw compute performance?

A: The NVIDIA GeForce GTX 1660 SUPER delivers 5.027 TFLOPS of FP32 compute, while the AMD Radeon Pro 560X delivers 2.056 TFLOPS. The NVIDIA card also reaches 10.05 TFLOPS of FP16, while the AMD card only manages 2.056 TFLOPS.

Q: How do the two compare in memory bandwidth?

A: The GTX 1660 SUPER has 336.0 GB/s of bandwidth from 6 GB of GDDR6 on a 192-bit bus. The Radeon Pro 560X has 94.08 GB/s from 4 GB of GDDR5 on a 128-bit bus.

Q: Which card can run in a laptop or compact system?

A: The Radeon Pro 560X is an integrated GPU with a 75 W TDP and no power connectors, suitable for portable devices. The GTX 1660 SUPER is a dual-slot discrete card with a 125 W TDP, a 300 W recommended PSU, and a single 8-pin connector.

Q: What are the DirectX and Vulkan support levels?

A: The Radeon Pro 560X supports DirectX 12 (12_0) and Vulkan 1.3. The GTX 1660 SUPER supports DirectX 12 (12_1) and Vulkan 1.4, giving it a higher feature level in both APIs.

Q: Which GPU has better OpenCL performance?

A: The GTX 1660 SUPER scores 52,490 in Geekbench OpenCL, which is 81.6 percent higher than the Radeon Pro 560X's 9,663.

Q: Are there any benchmarks where the Radeon Pro 560X wins?

A: No. The database records two head-to-head tests, and the GTX 1660 SUPER wins both. The Radeon Pro 560X has zero wins in the shared benchmark set.

Head-to-Head Benchmarks

The database includes two direct comparisons between these GPUs: Geekbench OpenCL and Geekbench Vulkan. Both are decisive wins for the NVIDIA GeForce GTX 1660 SUPER, and the margins are among the largest seen in this product segment.

Starting with Geekbench OpenCL, the GTX 1660 SUPER scores 52,490 while the Radeon Pro 560X scores 9,663. The delta is 81.6 percent in favor of the NVIDIA card. This test exercises general-purpose compute across the GPU's shading units, and the NVIDIA part has both more hardware and faster memory. With 1,408 shading units versus 1,024, and 336.0 GB/s of bandwidth versus 94.08 GB/s, the outcome aligns with the architectural difference. The GTX 1660 SUPER also has a higher FP32 throughput at 5.027 TFLOPS versus 2.056 TFLOPS, which is a 2.4x raw advantage that shows up directly in this workload.

In Geekbench Vulkan, the GTX 1660 SUPER scores 57,102 against 16,819 for the Radeon Pro 560X, a delta of 70.5 percent. Vulkan is a low-overhead API that scales well with hardware resources, so the NVIDIA card's larger TMU count (88 versus 64) and ROP count (48 versus 16) contribute heavily. The pixel rate difference is stark: 85.68 GPixel/s versus 16.06 GPixel/s. The texture rate is also far apart at 157.1 GTexel/s versus 64.26 GTexel/s. These fill-rate metrics explain why the NVIDIA card extends its lead in a graphics-adjacent compute test like Vulkan.

The GTX 1660 SUPER also holds a superior position in the broader database. Its average benchmark score is 12,986, placing it in the 53rd percentile among all GPUs. The Radeon Pro 560X has an average score of 15,082, which lands in the 57th percentile. This is an unusual situation where the higher average score belongs to the slower card in the head-to-head comparison. The explanation lies in the benchmark mix. The Radeon Pro 560X's average is pulled up by its Geekbench Metal score of 18,763, a test that the GTX 1660 SUPER does not participate in. The NVIDIA card's average is lowered by its Passmark DirectX 9, 10, 11, and 12 scores, which are all low numbers (189, 65, 104, and 50 respectively) that drag down its mean. The Geekbench OpenCL and Vulkan scores for the NVIDIA card are far higher than anything the AMD card produces, but the Passmark suite adds many low entries that the AMD card does not have.

Looking at the nearest rivals in the database, the GTX 1660 SUPER sits close to the NVIDIA GeForce RTX 3050 Ti Mobile (average score 12,940, delta 0.4 percent), the AMD Radeon RX 580 (12,928, delta 0.4 percent), and the AMD Radeon 740M (12,870, delta 0.9 percent). It trails the NVIDIA Tesla M2090 by 0.7 percent. The Radeon Pro 560X, meanwhile, sits near the NVIDIA GeForce GTX 660 Ti (15,063, delta 0.1 percent), the AMD Radeon RX 7600 (15,171, delta -0.6 percent), the NVIDIA GeForce RTX 3050 OEM (15,199, delta -0.8 percent), and the AMD Radeon 680M (15,270, delta -1.2 percent). These groupings confirm that the Radeon Pro 560X, despite its higher percentile, is surrounded by older or integrated-class parts, while the GTX 1660 SUPER competes in a more modern performance tier.

The data also shows the GTX 1660 SUPER has a robust set of additional benchmarks. Its Passmark G3D score of 12,699 and GPU Compute score of 5,076 are strong numbers for a 12 nm part. The G2D score of 805 indicates solid 2D performance, though that is not a relevant factor for most compute workloads. The DirectX 9 score of 189 and DirectX 11 score of 104 show legacy API performance, while the DirectX 12 score of 50 is lower, likely reflecting the benchmark's specific load pattern. None of these tests exist for the Radeon Pro 560X, so the comparison cannot be extended beyond the two shared Geekbench tests.

In summary, the recorded data leaves no ambiguity. The GTX 1660 SUPER outperforms the Radeon Pro 560X by 81.6 percent in OpenCL and 70.5 percent in Vulkan. It has more memory, faster memory, more shading units, more TMUs, more ROPs, higher pixel and texture rates, and higher compute throughput. The only advantage for the Radeon Pro 560X is its integrated form factor and lower power draw, which makes it the sole viable choice in systems that cannot physically accommodate a discrete dual-slot card. For any user with the ability to install a standard PCIe graphics card, the GTX 1660 SUPER is the superior product across every measurable dimension in this database.