AMD Radeon Pro 460 vs NVIDIA GeForce RTX 2070 SUPER Comparison

Head-to-Head Benchmarks

The data shows a decisive performance gap between these two GPUs. In the two shared benchmark tests, the NVIDIA GeForce RTX 2070 SUPER wins outright. The most dramatic result comes from Geekbench OpenCL, where the RTX 2070 SUPER scores 83,358 against the Radeon Pro 460’s 15,284. That translates to a 445.4% advantage, meaning the NVIDIA card delivers more than five times the compute throughput in this workload. Even in Geekbench Vulkan, which tends to favor AMD’s GCN architecture historically, the RTX 2070 SUPER posts 90,637 versus 16,816, a 439% lead. These are not marginal wins; they are generational obliterations.

Looking at the broader database averages, the RTX 2070 SUPER holds an average benchmark score of 20,282, while the Radeon Pro 460 averages 17,509. The NVIDIA card sits at the 65th percentile among all GPUs in the database, while the AMD part lands at the 61st percentile. On the surface, that percentile gap seems modest, but the head-to-head results reveal the real story: the RTX 2070 SUPER’s average is pulled down by its weaker DirectX legacy tests, whereas the Radeon Pro 460’s average is based on only three benchmarks, none of which are legacy DirectX tests. The disparity in raw compute is far larger than the percentile ranking suggests.

The RTX 2070 SUPER’s nearest rivals in the database include the NVIDIA Quadro M4000M (average score 20,480, delta -1%), the GeForce RTX 3070 Mobile (20,534, delta -1.2%), and Intel’s Arc B570 (20,556, delta -1.3%) and Arc A750 (20,582, delta -1.5%). This places the RTX 2070 SUPER essentially at parity with those cards, all within a 1.5% margin. For the Radeon Pro 460, its nearest rivals are the NVIDIA Tesla K40c (17,468, delta +0.2%), AMD Radeon Pro 560 (17,551, delta -0.2%), AMD Radeon 780M (17,588, delta -0.5%), and NVIDIA GeForce RTX 4060 (17,639, delta -0.7%). The Radeon Pro 460 is thus clustered with mid-range and integrated-class parts, while the RTX 2070 SUPER competes with modern discrete mid-range options.

The Verdict

The database is unambiguous: the NVIDIA GeForce RTX 2070 SUPER is the superior product for any workload that leverages compute, graphics, or modern APIs. The RTX 2070 SUPER wins 2 out of 2 head-to-head benchmarks, with deltas of 445.4% and 439%. No benchmark in the shared set favors the Radeon Pro 460. The AMD card’s highest recorded score is 20,426 in Geekbench Metal, a test the NVIDIA card does not appear in, but even that result is lower than the RTX 2070 SUPER’s average benchmark score of 20,282, which includes all its tests, not just its best one.

If the choice is between these two for a desktop build, the RTX 2070 SUPER is the only rational pick. Its 8 GB GDDR6 memory, 448.0 GB/s bandwidth, and 9.062 TFLOPS FP32 performance place it in a completely different class. The Radeon Pro 460, with 4 GB GDDR5, 81.28 GB/s bandwidth, and 1.858 TFLOPS FP32, is a mobile or compact form factor part. It was designed for portability and low power draw, not for demanding workloads. The data shows it trails the NVIDIA card by a factor of roughly five in OpenCL and Vulkan. No driver update or software optimization can close that gap.

For buyers who need a GPU for gaming, 3D rendering, or GPGPU compute, the RTX 2070 SUPER is the clear winner. For those who need a low-power embedded or Mac-compatible solution, the Radeon Pro 460 has its niche, but that niche is not performance. This is not a close contest.

Architecture Differences

The RTX 2070 SUPER uses the TU104 chip, built on TSMC’s 12 nm process, with 13,600 million transistors on a 545 mm² die. The Radeon Pro 460 uses the Baffin chip, fabricated by GlobalFoundries on a 14 nm process, with 3,000 million transistors on a 123 mm² die. The transistor density is nearly identical (25.0M per mm² for NVIDIA, 24.4M per mm² for AMD), which is expected given the similar node generations. However, the RTX 2070 SUPER packs over four times the transistors because its die is more than four times larger.

Architecturally, the RTX 2070 SUPER is based on Turing, which introduces dedicated RT (ray tracing) cores and Tensor cores. It has 40 RT cores and 320 Tensor cores. The Radeon Pro 460 is based on GCN 4.0, an architecture that predates hardware ray tracing and has no equivalent dedicated cores. The RTX 2070 SUPER supports DirectX 12 Ultimate (12_2), while the Radeon Pro 460 supports DirectX 12 (12_0). Both support OpenGL 4.6, but Vulkan support differs: the RTX 2070 SUPER runs Vulkan 1.4, while the Radeon Pro 460 runs Vulkan 1.3.

The memory subsystems are fundamentally different. The RTX 2070 SUPER uses GDDR6 with a 256-bit bus and 448.0 GB/s bandwidth. The Radeon Pro 460 uses GDDR5 with a 128-bit bus and 81.28 GB/s bandwidth. That is a 5.5x bandwidth advantage for NVIDIA. The RTX 2070 SUPER also has 2560 shading units, 160 TMUs, and 64 ROPs, compared to the Radeon Pro 460’s 1024 shading units, 64 TMUs, and 16 ROPs. Pixel rate and texture rate tell a similar story: 113.3 GPixel/s versus 14.51 GPixel/s, and 283.2 GTexel/s versus 58.05 GTexel/s.

The Radeon Pro 460 does have one architectural advantage: its FP16 throughput is 1.858 TFLOPS at a 1:1 ratio with FP32, meaning it does not sacrifice half-precision performance. The RTX 2070 SUPER’s FP16 is 18.12 TFLOPS at a 2:1 ratio, which is higher in absolute terms but indicates a different design priority. For workloads that rely on FP16, the RTX 2070 SUPER still wins on raw number, but the Radeon Pro 460 is more efficient in that specific ratio.

Specification Differences

| Specification | NVIDIA GeForce RTX 2070 SUPER | AMD Radeon Pro 460 |

|----------------|-------------------------------|--------------------|

| Process Node | 12 nm | 14 nm |

| Transistors | 13,600 million | 3,000 million |

| Die Size | 545 mm² | 123 mm² |

| Base Clock | 1605 MHz | 850 MHz |

| Boost Clock | 1770 MHz | 907 MHz |

| Memory Size | 8 GB | 4 GB |

| Memory Type | GDDR6 | GDDR5 |

| Memory Bus | 256 bit | 128 bit |

| Memory Bandwidth | 448.0 GB/s | 81.28 GB/s |

| Shading Units | 2560 | 1024 |

| TMUs | 160 | 64 |

| ROPs | 64 | 16 |

| Pixel Rate | 113.3 GPixel/s | 14.51 GPixel/s |

| Texture Rate | 283.2 GTexel/s | 58.05 GTexel/s |

| FP32 | 9.062 TFLOPS | 1.858 TFLOPS |

| FP16 | 18.12 TFLOPS (2:1) | 1.858 TFLOPS (1:1) |

| TDP | 215 W | 35 W |

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

| DirectX | 12 Ultimate (12_2) | 12 (12_0) |

| Vulkan | 1.4 | 1.3 |

| Release Date | 2019-07-08 | 2016-10-29 |

| Launch MSRP | 499 USD | Not available |

The RTX 2070 SUPER draws 215 W and requires a 550 W PSU, while the Radeon Pro 460 draws just 35 W and needs no external power connectors. The NVIDIA card is dual-slot and measures 267 mm long, 116 mm tall, and 35 mm wide. The AMD card is an IGP (integrated graphics processor) with no listed dimensions, designed to be soldered onto a board. Display outputs differ as well: the RTX 2070 SUPER offers HDMI 2.0, three DisplayPort 1.4a, and one USB Type-C, while the Radeon Pro 460 is listed as “Portable Device Dependent,” meaning its outputs vary by the host device.

FAQ

Q: Which GPU has higher raw compute performance?

A: The RTX 2070 SUPER delivers 9.062 TFLOPS FP32 and 18.12 TFLOPS FP16, versus the Radeon Pro 460’s 1.858 TFLOPS for both FP32 and FP16. In Geekbench OpenCL, the RTX 2070 SUPER scores 83,358 against 15,284, a 445.4% lead.

Q: Can the Radeon Pro 460 handle DirectX 12 Ultimate games?

A: No. The Radeon Pro 460 supports DirectX 12 (12_0), while the RTX 2070 SUPER supports DirectX 12 Ultimate (12_2), which includes features like hardware ray tracing and mesh shaders.

Q: How much memory bandwidth does each card have?

A: The RTX 2070 SUPER has 448.0 GB/s from its 256-bit GDDR6 interface. The Radeon Pro 460 has 81.28 GB/s from its 128-bit GDDR5 interface.

Q: Which card is better for a compact or low-power system?

A: The Radeon Pro 460 draws only 35 W, requires no power connectors, and is an IGP. The RTX 2070 SUPER draws 215 W, needs a 550 W PSU, and is dual-slot. For low-power compact builds, the Radeon Pro 460 fits, but its performance is far lower.

Q: What is the average benchmark score for each GPU?

A: The RTX 2070 SUPER averages 20,282 across all its recorded benchmarks. The Radeon Pro 460 averages 17,509. The RTX 2070 SUPER sits at the 65th percentile, the Radeon Pro 460 at the 61st.

Q: Does the Radeon Pro 460 support Vulkan?

A: Yes, it supports Vulkan 1.3. The RTX 2070 SUPER supports Vulkan 1.4. In the Vulkan benchmark, the RTX 2070 SUPER scores 90,637 versus 16,816 for the Radeon Pro 460.

Where Each One Wins

The RTX 2070 SUPER wins in every single head-to-head benchmark recorded in the database. That includes OpenCL and Vulkan compute workloads. It also wins decisively on memory bandwidth, texture rate, pixel rate, and shading unit count. Any workload that is GPU-bound, whether it is gaming, rendering, machine learning inference, or general compute, will favor the RTX 2070 SUPER. Its 8 GB GDDR6 frame buffer is double the Radeon Pro 460’s 4 GB GDDR5, which matters for modern games and large datasets. The RTX 2070 SUPER’s support for DirectX 12 Ultimate and Vulkan 1.4 means it can run the latest APIs, while the Radeon Pro 460 is limited to older feature sets.

The Radeon Pro 460 wins only in one narrow sense: power efficiency. At 35 W, it uses roughly one-sixth the power of the RTX 2070 SUPER’s 215 W. For a Mac or a portable device where the GPU is integrated and power is at a premium, the Radeon Pro 460 is the only viable option between the two, since the RTX 2070 SUPER is a discrete dual-slot card with external power connectors. The Radeon Pro 460 also has a 1:1 FP16 ratio, which could be relevant for certain niche compute tasks, but its absolute FP16 performance is still 1.858 TFLOPS versus 18.12 TFLOPS for the NVIDIA card.

In terms of the database’s nearest rivals, the RTX 2070 SUPER performs at a level consistent with the RTX 3070 Mobile and Intel Arc B570/A750, while the Radeon Pro 460 matches the performance of the Radeon 780M integrated graphics and the RTX 4060. That is a telling comparison: the Radeon Pro 460 is in the same performance class as modern integrated graphics, whereas the RTX 2070 SUPER is in the class of current discrete mid-range cards. For any use case where performance is the priority, the RTX 2070 SUPER is the definitive choice. For use cases where size, power, and integration are paramount, the Radeon Pro 460 has a role, but the data shows it is a different tier of hardware entirely.