AMD Radeon Pro 460 vs NVIDIA GeForce RTX 5090 D V2 Comparison

Head-to-Head Benchmarks

The data for these two GPUs cannot be compared through a shared benchmark suite, as the fact pack shows no overlapping test results. The AMD Radeon Pro 460 was evaluated using Geekbench Metal, OpenCL, and Vulkan tests, achieving scores of 20,426, 15,284, and 16,816 respectively. The NVIDIA GeForce RTX 5090 D V2 was assessed using a single 3DMark Steel Nomad DX12 test, scoring 16,504. With zero head-to-head benchmarks and zero wins recorded for either side, the direct comparison rests entirely on how each card performs within its own benchmark context relative to its nearest rivals.

The AMD Radeon Pro 460's average benchmark score of 17,509 places it in the 61st percentile of all GPUs. Its nearest rival, the NVIDIA Tesla K40c, scores 17,468, which is a 0.2% delta — meaning the Radeon Pro 460 is essentially tied with that card. Against the AMD Radeon Pro 560, the delta is -0.2%, with the rival scoring 17,551, so the Pro 460 trails by a hair. The AMD Radeon 780M scores 17,588, a -0.5% delta, and the NVIDIA GeForce RTX 4060 scores 17,639, a -0.7% delta. These margins are all under one percent, indicating that the Radeon Pro 460 sits in a very tight performance cluster where no rival holds a meaningful advantage.

The NVIDIA GeForce RTX 5090 D V2's single benchmark score of 16,504 yields a 59th percentile ranking, slightly below the Radeon Pro 460's 61st percentile. Its nearest rival, the NVIDIA T400, scores 16,508, representing a 0% delta — a dead heat. The AMD Radeon PRO W7500 scores 16,415, a 0.5% delta in favor of the RTX 5090 D V2. The NVIDIA RTX PRO 6000 Blackwell scores 16,408, a 0.6% delta, and the AMD Radeon RX 5700 XT scores 16,361, a 0.9% delta. None of these differences exceed one percent, so the RTX 5090 D V2 also occupies a tightly contested performance band, just slightly lower in absolute terms than the Radeon Pro 460's cluster.

Looking at the individual benchmark scores, the Radeon Pro 460's best result is its Geekbench Metal score of 20,426, which is 19.6% above its OpenCL score of 15,284 and 21.5% above its Vulkan score of 16,816. This suggests the architecture performs notably better under Apple's Metal API than under the more generic compute APIs. The RTX 5090 D V2, with only one benchmark result, shows no such API-dependent variation in the available data.

The percentile disparity is worth noting: despite the Radeon Pro 460 having a higher average score (17,509 vs 16,504) and a higher percentile (61 vs 59), the RTX 5090 D V2 is an active product while the Radeon Pro 460 is end-of-life. The benchmark contexts differ entirely — one set tests compute and graphics APIs, the other tests a specific DX12 workload — so the absolute score gap of 1,005 points should not be read as a performance hierarchy. The data simply shows that each card is competitive within its own reference group.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The AMD Radeon Pro 460 has an average benchmark score of 17,509, while the NVIDIA GeForce RTX 5090 D V2 has an average benchmark score of 16,504. The Radeon Pro 460 is 6.1% higher in this metric.

Q: How do the two GPUs rank against all other GPUs?

A: The AMD Radeon Pro 460 sits in the 61st percentile of all GPUs, while the NVIDIA GeForce RTX 5090 D V2 sits in the 59th percentile. The Radeon Pro 460 ranks two percentile points higher.

Q: What are the closest competitors for each GPU?

A: For the AMD Radeon Pro 460, the closest rival is the NVIDIA Tesla K40c with a 0.2% delta. For the NVIDIA GeForce RTX 5090 D V2, the closest rival is the NVIDIA T400 with a 0% delta, meaning an exact tie in average score.

Q: Which GPU has more shading units?

A: The NVIDIA GeForce RTX 5090 D V2 has 21,760 shading units, while the AMD Radeon Pro 460 has 1,024 shading units. The RTX 5090 D V2 has 21.3 times more shading units.

Q: What is the memory configuration difference?

A: The AMD Radeon Pro 460 has 4 GB of GDDR5 memory on a 128-bit bus with 81.28 GB/s bandwidth. The NVIDIA GeForce RTX 5090 D V2 has 24 GB of GDDR7 memory on a 384-bit bus with 1.34 TB/s bandwidth.

Q: Are there any shared benchmark results between the two?

A: No. The fact pack lists zero head-to-head benchmarks. The AMD Radeon Pro 460 was tested with Geekbench Metal, OpenCL, and Vulkan, while the NVIDIA GeForce RTX 5090 D V2 was tested with 3DMark Steel Nomad DX12.

The Verdict

The data points in opposite directions depending on the metric. The AMD Radeon Pro 460 holds a higher average benchmark score (17,509 vs 16,504) and a higher percentile rank (61 vs 59). Its nearest rivals are all within 0.7% of its score, and it shows strong Metal API performance with a Geekbench Metal score of 20,426. The NVIDIA GeForce RTX 5090 D V2, by contrast, has a lower average score but its nearest rival (NVIDIA T400) is a perfect 0% delta, and its other rivals are all within 0.9%. The RTX 5090 D V2 is an active product with a launch MSRP of 2,299 USD, while the Radeon Pro 460 is end-of-life.

For a user selecting based purely on the benchmark data available, the Radeon Pro 460 appears to be the stronger performer within its test suite, particularly in Metal-based workloads. However, the RTX 5090 D V2's single DX12 result cannot be directly compared to those API-specific scores. The production status difference — end-of-life versus active — suggests the RTX 5090 D V2 has ongoing support, while the Radeon Pro 460 does not. The RTX 5090 D V2 also has significantly more shading units (21,760 vs 1,024) and more memory (24 GB vs 4 GB), but these specifications do not translate into a higher benchmark score in the available data.

Specification Differences

The two GPUs differ across nearly every measurable specification. The AMD Radeon Pro 460 uses a 14 nm process node from GlobalFoundries, while the NVIDIA GeForce RTX 5090 D V2 uses a 5 nm process from TSMC. Transistor counts diverge sharply: 3,000 million for the Radeon Pro 460 versus 92,200 million for the RTX 5090 D V2. Die size also differs — 123 mm² for AMD versus 750 mm² for NVIDIA — leading to different transistor densities of 24.4M per mm² and 122.9M per mm² respectively.

Clock speeds show a gap: the Radeon Pro 460 runs at 850 MHz base and 907 MHz boost, while the RTX 5090 D V2 runs at 2017 MHz base and 2407 MHz boost. Memory clocks are 1270 MHz with 5.1 Gbps effective for AMD, and 1750 MHz with 28 Gbps effective for NVIDIA. The memory subsystems are entirely different: 4 GB GDDR5 on a 128-bit bus versus 24 GB GDDR7 on a 384-bit bus, yielding bandwidths of 81.28 GB/s and 1.34 TB/s.

Compute resources differ by an order of magnitude. The Radeon Pro 460 has 1,024 shading units, 64 TMUs, and 16 ROPs. The RTX 5090 D V2 has 21,760 shading units, 680 TMUs, and 176 ROPs, plus 170 ray tracing cores and 680 tensor cores — features the Radeon Pro 460 lacks entirely. Pixel rate is 14.51 GPixel/s versus 423.6 GPixel/s, and texture rate is 58.05 GTexel/s versus 1,636.8 GTexel/s. FP32 performance is 1.858 TFLOPS versus 104.8 TFLOPS, with both offering 1:1 FP16.

Power and physical specs also diverge. The Radeon Pro 460 has a 35 W TDP with no power connectors, while the RTX 5090 D V2 has a 575 W TDP, requires one 16-pin connector, and a suggested PSU of 950 W. The Radeon Pro 460 is an IGP (integrated graphics package), while the RTX 5090 D V2 is dual-slot with dimensions of 304 mm length, 137 mm height, and 48 mm width. Bus interfaces are PCIe 3.0 x8 versus PCIe 5.0 x16. Display outputs are portable-device-dependent for AMD, while NVIDIA offers 1x HDMI 2.1b and 3x DisplayPort 2.1b.

Architecture Differences

The architecture gap is fundamental. The AMD Radeon Pro 460 is built on GCN 4.0 with the Baffin chip, part of the Radeon Pro Mac (400 Series) generation. It uses a 14 nm process from GlobalFoundries with 3,000 million transistors on a 123 mm² die. The NVIDIA GeForce RTX 5090 D V2 is built on Blackwell 2.0 with the GB202 chip, part of the GeForce 50 series. It uses a 5 nm process from TSMC with 92,200 million transistors on a 750 mm² die.

The Radeon Pro 460 has no ray tracing cores and no tensor cores. The RTX 5090 D V2 includes 170 ray tracing cores and 680 tensor cores, enabling hardware-accelerated ray tracing and AI processing that the GCN architecture cannot provide. The transistor density difference — 24.4M per mm² versus 122.9M per mm² — reflects the process node advancement from 14 nm to 5 nm.

API support differs: the Radeon Pro 460 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. The RTX 5090 D V2 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The DirectX 12_2 Ultimate tier on NVIDIA enables features like mesh shaders and variable rate shading that are absent from the AMD card's 12_0 tier. The Vulkan version difference (1.3 vs 1.4) also indicates newer feature availability on the NVIDIA side.

The release dates are separated by nearly nine years: October 29, 2016 for the Radeon Pro 460, and August 14, 2025 for the RTX 5090 D V2. The Radeon Pro 460 is end-of-life with no successor listed, while the RTX 5090 D V2 lists a predecessor (GeForce 40) and a successor (GeForce 60). The Radeon Pro 460 belongs to the Radeon Pro Mac generation, indicating its design target was Apple Mac systems, whereas the RTX 5090 D V2 belongs to the GeForce 50 generation with a standard desktop form factor.

Where Each One Wins

The AMD Radeon Pro 460 wins in benchmark score metrics. Its average benchmark score of 17,509 exceeds the RTX 5090 D V2's 16,504, and its 61st percentile ranking beats the 59th percentile of the NVIDIA card. In Geekbench Metal, the Radeon Pro 460 achieves 20,426, which is its strongest result and indicates a particular strength in Apple's graphics API. Its OpenCL score of 15,284 and Vulkan score of 16,816 are lower but still contribute to a higher overall average than the RTX 5090 D V2's single result. The Radeon Pro 460 also wins on power efficiency: 35 W TDP versus 575 W, a 16.4x difference, and it requires no power connectors while the RTX 5090 D V2 needs a 16-pin connector and a 950 W PSU.

The NVIDIA GeForce RTX 5090 D V2 wins on raw specifications and active support. It has 21,760 shading units versus 1,024, 680 TMUs versus 64, and 176 ROPs versus 16. Memory capacity is 24 GB versus 4 GB, and bandwidth is 1.34 TB/s versus 81.28 GB/s — a 16.5x difference. Clock speeds are higher (2407 MHz boost vs 907 MHz boost), and FP32 compute is 104.8 TFLOPS versus 1.858 TFLOPS. The RTX 5090 D V2 includes ray tracing and tensor cores that the Radeon Pro 460 lacks entirely. Its production status is active, while the Radeon Pro 460 is end-of-life. The RTX 5090 D V2 also wins on API support with DirectX 12 Ultimate and Vulkan 1.4.

In terms of nearest rival deltas, the RTX 5090 D V2 has a tighter competitive margin: its top rival (NVIDIA T400) is at 0% delta, meaning a perfect tie, while the Radeon Pro 460's closest rival (NVIDIA Tesla K40c) is at 0.2% delta. The RTX 5090 D V2 also shows a 0.9% win over its weakest rival (AMD Radeon RX 5700 XT), while the Radeon Pro 460 shows a 0.7% deficit to its weakest rival (NVIDIA GeForce RTX 4060). This suggests the RTX 5090 D V2 is slightly more dominant within its reference group, even though its absolute score is lower.

The use-case split is clear from the data. The Radeon Pro 460 suits scenarios where Metal API performance matters, where power draw must be minimal, and where the 35 W TDP and IGP form factor fit constrained systems. The RTX 5090 D V2 suits scenarios requiring maximum memory capacity, high-bandwidth GDDR7, hardware ray tracing, tensor core acceleration, and active production support with a defined successor path. The benchmark scores do not reflect the specification gap, so users prioritizing raw compute resources should favor the RTX 5090 D V2, while those prioritizing benchmark scores and power efficiency should favor the Radeon Pro 460.