AMD Radeon Pro 560 vs NVIDIA GeForce RTX 2060 SUPER Comparison

FAQ

Q: How much faster is the NVIDIA GeForce RTX 2060 SUPER than the AMD Radeon Pro 560 in OpenCL?

A: The RTX 2060 SUPER scores 76,957 in Geekbench OpenCL, which is 396.4% ahead of the Radeon Pro 560's 15,504. That is a roughly five-fold advantage in raw compute throughput.

Q: Does the AMD Radeon Pro 560 win any benchmark between the two?

A: No. In the head-to-head data, the RTX 2060 SUPER wins both available tests (Geekbench OpenCL and Geekbench Vulkan). The Radeon Pro 560 has zero wins.

Q: What is the average benchmark score difference between these two cards?

A: The RTX 2060 SUPER averages 18,093 across all benchmarks, while the Radeon Pro 560 averages 17,551. That is a 3.1% gap in favor of the NVIDIA card, despite the NVIDIA part winning the head-to-head tests by huge margins.

Q: How does the Radeon Pro 560 compare to its closest rivals?

A: The Radeon Pro 560 sits at the 61st percentile of all GPUs. Its nearest rival is the AMD Radeon 780M, which scores 17,588, just 0.2% higher. The Radeon Pro 460 trails by 0.2%, and the Tesla K40c trails by 0.5%.

Q: What is the RTX 2060 SUPER's position among all GPUs?

A: The RTX 2060 SUPER sits at the 62nd percentile. Its closest rival is the RTX 3060 Mobile at 18,159 (0.4% lower), followed by the Radeon Pro 5700 at 18,189 (0.5% lower). The RX 460 and Arc A770M are 1.5% and 1.6% lower, respectively.

Q: Does the Radeon Pro 560 support hardware ray tracing?

A: No. The Radeon Pro 560 has no RT cores listed, while the RTX 2060 SUPER includes 34 RT cores and 272 tensor cores. The AMD card also lacks a DirectX 12 Ultimate designation, supporting only DirectX 12 (12_0).

The Verdict

The data is unambiguous: the NVIDIA GeForce RTX 2060 SUPER is the faster card by every measured metric. It wins both head-to-head benchmarks with deltas of 396.4% (OpenCL) and 376.8% (Vulkan). The average benchmark scores tell a similar story, though with a much narrower gap — 18,093 versus 17,551. That 3.1% average advantage masks the extreme disparity in the compute-heavy tests where the NVIDIA card dominates.

For a workstation or desktop user needing raw compute performance, the RTX 2060 SUPER is the clear choice. Its 7.181 TFLOPS FP32 throughput dwarfs the Radeon Pro 560's 1.858 TFLOPS. The RTX 2060 SUPER also brings 8 GB of GDDR6 memory on a 256-bit bus, delivering 448.0 GB/s of bandwidth — more than five times the 81.28 GB/s of the Radeon Pro 560.

However, the Radeon Pro 560 is a different class of product entirely. It is an integrated graphics processor (IGP) with a 75 W TDP and no power connectors, designed for portable Mac systems. Its display outputs are listed as "Portable Device Dependent," indicating it is not a standalone desktop card. For users constrained to that form factor, the Radeon Pro 560 is the only option in this comparison.

The RTX 2060 SUPER launched at 399 USD MSRP and is now end-of-life. The Radeon Pro 560 has no launch MSRP listed and is also end-of-life. Neither card is current, but the RTX 2060 SUPER remains the more capable part by a substantial margin.

In short: if you can install a dual-slot, 175 W card with an 8-pin connector, the RTX 2060 SUPER wins outright. If you need an IGP for a compact Mac, the Radeon Pro 560 is what the data supports — there is no performance argument for it otherwise.

Head-to-Head Benchmarks

The Geekbench OpenCL test shows the largest single disparity. The RTX 2060 SUPER scores 76,957 against the Radeon Pro 560's 15,504, a 396.4% delta. That is not a marginal win; it is a generational chasm. The NVIDIA card's FP32 throughput of 7.181 TFLOPS versus 1.858 TFLOPS explains the magnitude — the RTX 2060 SUPER has nearly four times the raw shader compute, and the test reflects that.

Geekbench Vulkan narrows the gap slightly but not meaningfully. The RTX 2060 SUPER posts 77,402, while the Radeon Pro 560 manages 16,232. The delta is 376.8%. Vulkan support differs as well: the RTX 2060 SUPER supports Vulkan 1.4, while the Radeon Pro 560 is limited to Vulkan 1.3. The newer API version on the NVIDIA card likely contributes to its stronger Vulkan showing.

The average benchmark scores present a more nuanced picture. The RTX 2060 SUPER's average of 18,093 is drawn from ten benchmarks, including DirectX 9 through 12, OpenCL, Vulkan, and compute tests. The Radeon Pro 560's average of 17,551 is drawn from only three benchmarks (Metal, OpenCL, Vulkan). This discrepancy in test coverage means the averages are not directly comparable — the NVIDIA card's average includes legacy DirectX tests where it scores far lower (e.g., 61 in Passmark DirectX 12, 111 in DirectX 10), pulling its average down.

The RTX 2060 SUPER's percentile ranking of 62 versus the Radeon Pro 560's 61 shows both cards sit near the same overall position among all GPUs. Yet the head-to-head deltas tell a different story. The explanation is that the Radeon Pro 560's nearest rivals — the Radeon 780M, Radeon Pro 460, and Tesla K40c — are all within 0.5% of its score. The RTX 2060 SUPER's rivals are also tightly clustered, but the two cards themselves are not close in the tests they share.

Specification Differences

The memory subsystems are fundamentally different. The RTX 2060 SUPER has 8 GB of GDDR6 on a 256-bit bus, yielding 448.0 GB/s bandwidth. The Radeon Pro 560 has 4 GB of GDDR5 on a 128-bit bus, yielding 81.28 GB/s. That is a 5.5x bandwidth advantage for the NVIDIA card, which directly impacts texture-heavy workloads.

Shading resources follow the same pattern. The RTX 2060 SUPER has 2,176 shading units, 136 texture mapping units, and 64 ROPs. The Radeon Pro 560 has 1,024 shading units, 64 TMUs, and 16 ROPs. The pixel rate is 105.6 GPixel/s versus 14.51 GPixel/s, and the texture rate is 224.4 GTexel/s versus 58.05 GTexel/s.

FP16 performance diverges sharply. The RTX 2060 SUPER delivers 14.36 TFLOPS at a 2:1 ratio, while the Radeon Pro 560 delivers 1.858 TFLOPS at a 1:1 ratio. This means the NVIDIA card has dedicated FP16 throughput that is nearly 8x higher, while the AMD card's FP16 equals its FP32.

Power and physical specifications are in different leagues. The RTX 2060 SUPER draws 175 W, requires a 450 W PSU, uses a single 8-pin connector, and is a dual-slot card measuring 229 mm long. The Radeon Pro 560 draws 75 W, has no power connectors, and is an IGP. The bus interface also differs: PCIe 3.0 x16 for NVIDIA, PCIe 3.0 x8 for AMD.

Display outputs show another divide. The RTX 2060 SUPER offers 1x DVI, 1x HDMI 2.0, 2x DisplayPort 1.4a, and 1x USB Type-C. The Radeon Pro 560's outputs are "Portable Device Dependent," meaning they are determined by the host system.

Architecture Differences

The RTX 2060 SUPER is built on NVIDIA's Turing architecture using the TU106 chip at TSMC's 12 nm process. The die measures 445 mm² and contains 10,800 million transistors. The Radeon Pro 560 uses AMD's GCN 4.0 architecture with the Polaris 21 chip at GlobalFoundries' 14 nm process. Its die is 123 mm² with 3,000 million transistors. Transistor density is nearly identical — 24.3M per mm² for NVIDIA versus 24.4M per mm² for AMD — but the total transistor count is 3.6x higher on the NVIDIA chip.

The RTX 2060 SUPER includes hardware features the AMD card lacks entirely: 34 RT cores for ray tracing and 272 tensor cores for AI workloads. The Radeon Pro 560 has neither. This is the defining architectural difference. The Turing card supports DirectX 12 Ultimate (12_2), while the Radeon Pro 560 only reaches DirectX 12 (12_0). Vulkan support also differs, with the NVIDIA card at 1.4 and the AMD card at 1.3. Both support OpenGL 4.6.

The Radeon Pro 560 belongs to the Radeon Pro Mac 500 Series generation, released in April 2017. The RTX 2060 SUPER is from the GeForce 20 series, released in July 2019. The NVIDIA card's predecessor is GeForce 10, and its successor is GeForce 30. The AMD card has no listed predecessor or successor.

Clock speeds are not directly comparable because the Radeon Pro 560 has no listed base or boost clock. The RTX 2060 SUPER runs at 1470 MHz base and 1650 MHz boost. Memory clocks differ as well: 1750 MHz (14 Gbps effective) for the NVIDIA card versus 1270 MHz (5.1 Gbps effective) for the AMD card.

The process node and foundry differences — 12 nm TSMC versus 14 nm GlobalFoundries — explain part of the efficiency gap, but the architectural gulf is larger. GCN 4.0 is a 2016-era design, while Turing is a 2018 design with dedicated ray tracing and tensor cores. The benchmark data reflects that generational leap.