AMD Radeon Pro 560 vs NVIDIA GeForce RTX 2070 SUPER Comparison

Head-to-Head Benchmarks

The recorded data shows a decisive performance gap between the NVIDIA GeForce RTX 2070 SUPER and the AMD Radeon Pro 560 in the two shared benchmark tests. Both tests are compute-oriented APIs, and the results are not close.

In Geekbench OpenCL, the RTX 2070 SUPER scores 83,358 points against the Radeon Pro 560's 15,504 points. That is a delta of 437.7%, meaning the NVIDIA card delivers more than five times the OpenCL compute throughput of the AMD part. The Geekbench Vulkan result follows a similar pattern: the RTX 2070 SUPER posts 90,637 points, while the Radeon Pro 560 manages 16,232 points, a 458.4% advantage for the NVIDIA card.

It is worth remembering the Radeon Pro 560 also has a Geekbench Metal score of 20,918, which is not directly comparable because the RTX 2070 SUPER was not tested under Metal. However, even if we set that aside, the OpenCL and Vulkan deltas are so large that no single API result would change the overall picture. The head-to-head tally is 2 wins for the RTX 2070 SUPER and 0 for the Radeon Pro 560.

To put the NVIDIA card's average score in context, the database places it at the 65th percentile of all GPUs, with an average benchmark score of 20,282. Its nearest rivals include the NVIDIA Quadro M4000M (20,480, -1%), the GeForce RTX 3070 Mobile (20,534, -1.2%), the Intel Arc B570 (20,556, -1.3%), and the Intel Arc A750 (20,582, -1.5%). All four rivals are within 1.5% of the RTX 2070 SUPER, indicating that it sits in a tightly packed performance tier. The Radeon Pro 560, by contrast, sits at the 61st percentile with an average score of 17,551, which places it near the AMD Radeon 780M (17,588, -0.2%), the AMD Radeon Pro 460 (17,509, +0.2%), the NVIDIA Tesla K40c (17,468, +0.5%), and the NVIDIA GeForce RTX 4060 (17,639, -0.5%). The Radeon Pro 560's closest rivals are all within 0.5% of its average, showing that it is not an outlier in its own tier, but that tier is substantially lower than the RTX 2070 SUPER's.

The average score gap between the two cards is 2,731 points (20,282 vs 17,551), which is roughly 15.5% in favor of the NVIDIA card when measured against the AMD part's average. However, the head-to-head deltas are far larger because the shared tests are compute-heavy, and the RTX 2070 SUPER's architecture is simply more capable in that domain.

FAQ

Q: Which card wins in Geekbench OpenCL, and by how much?

A: The NVIDIA GeForce RTX 2070 SUPER wins with 83,358 points versus 15,504 for the AMD Radeon Pro 560, a delta of 437.7%.

Q: Is the Vulkan result similar to the OpenCL result?

A: Yes, the RTX 2070 SUPER scores 90,637 in Geekbench Vulkan, while the Radeon Pro 560 scores 16,232, a 458.4% advantage for the NVIDIA card.

Q: Does the Radeon Pro 560 have any benchmark where it beats the RTX 2070 SUPER?

A: In the shared head-to-head tests, no. The Radeon Pro 560 has a Geekbench Metal score of 20,918, but the RTX 2070 SUPER was not tested in Metal, so no direct comparison exists.

Q: How does the RTX 2070 SUPER compare to its nearest rivals?

A: Its average score of 20,282 is within 1.5% of the Quadro M4000M, RTX 3070 Mobile, Arc B570, and Arc A750, all of which sit between 20,480 and 20,582.

Q: What is the percentile ranking for each card?

A: The RTX 2070 SUPER is at the 65th percentile of all GPUs, while the Radeon Pro 560 is at the 61st percentile.

Q: Are both cards still in production?

A: No. Both are marked as end-of-life in the database.

The Verdict

The data is unambiguous: the NVIDIA GeForce RTX 2070 SUPER outperforms the AMD Radeon Pro 560 in every directly comparable benchmark. If the workload is OpenCL or Vulkan compute, the RTX 2070 SUPER is the clear choice, delivering 437.7% and 458.4% higher scores respectively. The Radeon Pro 560's only unique benchmark, Metal, cannot be compared, but its score of 20,918 does not suggest it would close a gap of that magnitude.

For users who need maximum compute throughput in cross-platform APIs, the RTX 2070 SUPER is the only rational pick from these two. The Radeon Pro 560 may be acceptable for legacy Mac-oriented workflows where Metal is the primary API, but the database shows no scenario in the shared tests where it wins. The RTX 2070 SUPER also has a higher average benchmark score (20,282 vs 17,551) and a higher percentile rank (65 vs 61), reinforcing its overall advantage.

The Radeon Pro 560 should only be considered if the target environment is strictly Metal-based and the application cannot use OpenCL or Vulkan. In that narrow case, the RTX 2070 SUPER has no recorded Metal score, so the AMD card is not directly inferior. But for any general compute task, the RTX 2070 SUPER is superior by a wide margin.

Specification Differences

The two cards differ in nearly every measurable specification. The RTX 2070 SUPER uses 8 GB of GDDR6 memory on a 256-bit bus, delivering 448.0 GB/s of bandwidth, while the Radeon Pro 560 has 4 GB of GDDR5 on a 128-bit bus, with 81.28 GB/s. The NVIDIA card has 2,560 shading units, 160 texture mapping units, and 64 ROPs, versus 1,024 shading units, 64 TMUs, and 16 ROPs for the AMD card.

The RTX 2070 SUPER features 40 ray tracing cores and 320 tensor cores; the Radeon Pro 560 has none. Pixel rate is 113.3 GPixel/s for the NVIDIA card and 14.51 GPixel/s for the AMD card, while texture rates are 283.2 GTexel/s and 58.05 GTexel/s respectively. FP32 throughput is 9.062 TFLOPS versus 1.858 TFLOPS, and FP16 is 18.12 TFLOPS (2:1) versus 1.858 TFLOPS (1:1). The RTX 2070 SUPER has a 215 W TDP and requires a 550 W PSU, while the Radeon Pro 560 has a 75 W TDP and uses no power connectors. The NVIDIA card is dual-slot with a 267 mm length, 116 mm height, and 35 mm width; the AMD card is an IGP with no listed dimensions. The RTX 2070 SUPER uses PCIe 3.0 x16, and the Radeon Pro 560 uses PCIe 3.0 x8. Display outputs also differ: the NVIDIA card has 1x HDMI 2.0, 3x DisplayPort 1.4a, and 1x USB Type-C, while the AMD card is "Portable Device Dependent."

Architecture Differences

The RTX 2070 SUPER is built on NVIDIA's Turing architecture, using the TU104 chip fabricated on TSMC's 12 nm process. It contains 13,600 million transistors on a 545 mm² die, giving a transistor density of 25.0M per mm². The Radeon Pro 560 uses AMD's GCN 4.0 architecture, with the Polaris 21 chip on GlobalFoundries' 14 nm process. It has 3,000 million transistors on a 123 mm² die, a density of 24.4M per mm². The NVIDIA card's architecture includes dedicated ray tracing and tensor cores, which the AMD card lacks. The RTX 2070 SUPER supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4; the Radeon Pro 560 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. The NVIDIA card's FP16 throughput is doubled relative to FP32 (2:1), while the AMD card runs FP16 at the same rate as FP32 (1:1). The release dates are 2019-07-08 for the NVIDIA card and 2017-04-17 for the AMD card, with the Radeon Pro 560 belonging to the Radeon Pro Mac (500 Series) generation.

Where Each One Wins

The RTX 2070 SUPER wins in every shared benchmark category. In compute-heavy workloads such as OpenCL and Vulkan, it is not merely ahead; it is multiple times faster. The 437.7% OpenCL delta and 458.4% Vulkan delta indicate that any application using these APIs will see a transformative performance uplift on the NVIDIA card. The RTX 2070 SUPER also has higher pixel and texture rates, more memory bandwidth, and double the FP32 throughput, making it superior for general-purpose GPU compute, 3D rendering, and any graphics workload that scales with raw throughput.

The Radeon Pro 560 has no wins in the shared tests. Its only recorded benchmark not shared with the RTX 2070 SUPER is Geekbench Metal, where it scores 20,918. In a hypothetical Metal-only environment where OpenCL and Vulkan are unavailable or unsupported, the Radeon Pro 560 would be the only option of the two, since the RTX 2070 SUPER has no Metal score in the database. However, that is a scenario defined by absence of data, not by demonstrated superiority. For users constrained to a Mac ecosystem that requires Metal, the Radeon Pro 560 is the pick by default, but the database offers no evidence that it would outperform the RTX 2070 SUPER if both were tested under the same API. For any other use case, the RTX 2070 SUPER is the definitive choice.