AMD Radeon Pro 450 vs NVIDIA GeForce GTX 460 v2 Comparison

Where Each One Wins

The benchmark data splits cleanly between these two cards, but the split is narrow. The AMD Radeon Pro 450 wins the only shared test, but the margin is small enough that the real story is about suitability, not dominance.

In the Geekbench OpenCL test, the AMD Radeon Pro 450 scores 9002 against 8743 for the NVIDIA GeForce GTX 460 v2, a 3% advantage. That is the sole head-to-head measurement recorded. The AMD card also has two additional benchmark entries in the database: a Geekbench Metal score of 12893 and a Geekbench Vulkan score of 10518. The NVIDIA card has no Metal or Vulkan results recorded, so those workloads are simply unavailable for comparison.

The NVIDIA GeForce GTX 460 v2 wins no recorded benchmark against the AMD card. Its only entry is that OpenCL score, which trails by 259 points. Looking at the broader percentile ranks, the AMD Radeon Pro 450 sits at the 49th percentile of all GPUs, while the GTX 460 v2 sits at the 44th. The AMD card's average benchmark score across all recorded tests is 10804, whereas the NVIDIA card averages 8743.

For use-case decisions, the AMD Radeon Pro 450 is the card for anyone working in Metal-centric environments (macOS applications) or Vulkan workloads, since those scores exist and are strong relative to its OpenCL result. The NVIDIA GeForce GTX 460 v2, by contrast, offers nothing beyond OpenCL in the recorded data, and even there it is slightly behind. The GTX 460 v2's only advantage is that it is a physically larger card with more texture units and ROPs, which suggests it was designed for a different era of desktop rendering, but the numbers do not show a workload where that hardware translates into a win.

Architecture Differences

The two cards come from fundamentally different engineering generations. The AMD Radeon Pro 450 uses the Baffin chip built on GCN 4.0 architecture, fabricated on a 14 nm process at GlobalFoundries. The NVIDIA GeForce GTX 460 v2 uses the GF114 chip on Fermi 2.0 architecture, built on a 40 nm process at TSMC. That process gap is enormous: 14 nm versus 40 nm. The AMD card fits 3,000 million transistors onto a 123 mm² die, giving a transistor density of 24.4 million per mm². The NVIDIA card packs 1,950 million transistors into a 332 mm² die, for a density of just 5.9 million per mm².

The memory systems differ in capacity and bus width. The AMD Radeon Pro 450 has 2 GB of GDDR5 on a 128-bit bus, delivering 81.28 GB/s of bandwidth. The NVIDIA card has 1024 MB (1 GB) of GDDR5 on a wider 192-bit bus, giving 96.19 GB/s. So the NVIDIA card has roughly 18% more memory bandwidth, but half the capacity. The AMD card's memory clock is 1270 MHz (5.1 Gbps effective), while the NVIDIA card runs at 1002 MHz (4 Gbps effective).

Compute resources are inverted in a revealing way. The AMD card has 640 shading units, 40 texture mapping units, and 16 ROPs. The NVIDIA card has 336 shading units, 56 TMUs, and 24 ROPs. That means NVIDIA packs more texture and pixel throughput per shader, while AMD packs more raw shader count. The pixel rate is 12.80 GPixel/s for AMD versus 10.91 GPixel/s for NVIDIA, so AMD wins that race. The texture rate is 43.62 GTexel/s for NVIDIA versus 32.00 GTexel/s for AMD, so NVIDIA wins texturing. The FP32 output is nearly tied: 1,024.0 GFLOPS for AMD and 1,046.3 GFLOPS for NVIDIA. The AMD card also supports FP16 at 1,024.0 GFLOPS (1:1 ratio), while the NVIDIA card has no recorded FP16 capability.

API support differs meaningfully. The AMD card supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. The NVIDIA card supports DirectX 12 (11_0) and OpenGL 4.6, but has no Vulkan entry. This explains the benchmark gap: the GTX 460 v2 simply cannot run Vulkan tests, and its DirectX 12 support is the earlier 11_0 feature level.

Power and physical design are opposite ends of the spectrum. The AMD Radeon Pro 450 draws 35 W and comes as an MXM Module, typical for laptops and all-in-one systems. The NVIDIA GeForce GTX 460 v2 draws 160 W, uses a dual-slot cooler, requires two 6-pin power connectors, and needs a 450 W power supply. The NVIDIA card is 210 mm (8.3 inches) long. The AMD card has no recorded length, as its form factor is portable-device dependent.

Head-to-Head Benchmarks

The only direct comparison available is Geekbench OpenCL. The AMD Radeon Pro 450 scores 9002, the NVIDIA GeForce GTX 460 v2 scores 8743. The delta is 3% in favor of AMD. That is a narrow win, but it is consistent with the average benchmark scores: AMD averages 10804 across three tests, NVIDIA averages 8743 across one.

The bigger wins for AMD come from the tests the NVIDIA card cannot run. The AMD Radeon Pro 450's Metal score of 12893 is 43% higher than its own OpenCL score. Its Vulkan score of 10518 is 17% higher than its OpenCL score. These are not rival comparisons, but they show that the AMD card scales well across modern APIs. The GTX 460 v2 has no corresponding data, so its performance in those APIs is unknown but likely absent given the lack of Vulkan support in its specification.

Looking at the nearest rivals for context, the AMD Radeon Pro 450's average score of 10804 places it 0.4% ahead of the NVIDIA Quadro K2200 (10761), 0.7% behind the NVIDIA GeForce MX350 (10883), 1.1% ahead of the NVIDIA GeForce GTX 560 Ti (10690), and 1.7% ahead of the AMD Radeon RX 6600S (10629). The NVIDIA GeForce GTX 460 v2's average of 8743 is essentially tied with the NVIDIA GeForce RTX 3050 A Mobile (8746, 0% delta), 0.7% ahead of the NVIDIA Quadro P2200 (8686), 1.2% behind the AMD Radeon R9 M265X (8851), and 1.4% behind the AMD Radeon Pro WX 5100 (8863). So both cards sit in crowded mid-pack territory, but the AMD card sits about 20% higher in absolute average score (10804 versus 8743).

FAQ

Q: Which card has the higher average benchmark score?

A: The AMD Radeon Pro 450 has an average benchmark score of 10804 across three tests (Metal, OpenCL, Vulkan). The NVIDIA GeForce GTX 460 v2 has an average of 8743 from a single OpenCL test.

Q: Does the NVIDIA card support Vulkan?

A: No. The NVIDIA GeForce GTX 460 v2 has no Vulkan API entry in its specification. It supports DirectX 12 (11_0) and OpenGL 4.6. The AMD Radeon Pro 450 supports Vulkan 1.3.

Q: What is the memory capacity difference?

A: The AMD Radeon Pro 450 has 2 GB of GDDR5. The NVIDIA GeForce GTX 460 v2 has 1024 MB (1 GB) of GDDR5. The NVIDIA card has a wider 192-bit bus, giving 96.19 GB/s bandwidth, while the AMD card uses a 128-bit bus for 81.28 GB/s.

Q: Which card has more shading units?

A: The AMD Radeon Pro 450 has 640 shading units. The NVIDIA GeForce GTX 460 v2 has 336. However, the NVIDIA card has 56 texture mapping units and 24 ROPs versus 40 TMUs and 16 ROPs for AMD.

Q: Why does the NVIDIA card have no Metal benchmark score?

A: The database records no Metal test for the NVIDIA GeForce GTX 460 v2. The AMD Radeon Pro 450 scores 12893 in Geekbench Metal. The NVIDIA card's only recorded benchmark is Geekbench OpenCL at 8743.

Q: What is the power draw difference?

A: The AMD Radeon Pro 450 has a TDP of 35 W and uses an MXM Module form factor. The NVIDIA GeForce GTX 460 v2 has a TDP of 160 W, is dual-slot, requires two 6-pin power connectors, and a 450 W power supply.

Specification Differences

| Field | AMD Radeon Pro 450 | NVIDIA GeForce GTX 460 v2 |

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

| Chip | Baffin | GF114 |

| Architecture | GCN 4.0 | Fermi 2.0 |

| Process Node | 14 nm | 40 nm |

| Foundry | GlobalFoundries | TSMC |

| Transistors | 3,000 million | 1,950 million |

| Die Size | 123 mm² | 332 mm² |

| Transistor Density | 24.4M / mm² | 5.9M / mm² |

| Memory Clock | 1270 MHz (5.1 Gbps effective) | 1002 MHz (4 Gbps effective) |

| Memory Size | 2 GB | 1024 MB |

| Memory Bus Width | 128 bit | 192 bit |

| Memory Bandwidth | 81.28 GB/s | 96.19 GB/s |

| Shading Units | 640 | 336 |

| TMUs | 40 | 56 |

| ROPs | 16 | 24 |

| Pixel Rate | 12.80 GPixel/s | 10.91 GPixel/s |

| Texture Rate | 32.00 GTexel/s | 43.62 GTexel/s |

| FP32 | 1,024.0 GFLOPS | 1,046.3 GFLOPS |

| FP16 | 1,024.0 GFLOPS (1:1) | null |

| TDP | 35 W | 160 W |

| Slot Width | MXM Module | Dual-slot |

| Power Connectors | null | 2x 6-pin |

| Suggested PSU | null | 450 W |

| Bus Interface | PCIe 3.0 x8 | PCIe 2.0 x16 |

| Display Outputs | Portable Device Dependent | 2x DVI, 1x mini-HDMI 1.3a |

| DirectX | 12 (12_0) | 12 (11_0) |

| Vulkan | 1.3 | null |

| Length | null | 210 mm (8.3 inches) |

| Release Date | 2016-10-29 | 2011-09-23 |

| Predecessor | null | GeForce 200 |

| Successor | null | GeForce 500 |

| Launch MSRP | null | 199 USD |

The Verdict

The AMD Radeon Pro 450 is the pick for modern, API-diverse workloads. It wins the only head-to-head benchmark (3% in OpenCL), adds strong Metal and Vulkan scores, uses 35 W instead of 160 W, fits in portable devices, and has 2 GB of memory. Its 49th percentile rank and 10804 average score place it clearly above the NVIDIA card's 44th percentile and 8743 average.

The NVIDIA GeForce GTX 460 v2 is a card from a different era, and the data does not favor it in any recorded test. Its wider 192-bit bus and higher texture rate (43.62 GTexel/s) are its only quantitative strengths, but those do not translate into a benchmark win. Its 1024 MB memory capacity and lack of Vulkan support are significant handicaps. The 160 W power draw and dual-slot requirement make it a desktop-only option, and even there it needs a 450 W power supply.

Anyone relying on Metal or Vulkan should choose the AMD Radeon Pro 450 without hesitation. Anyone working in OpenCL-only environments will find the AMD card still 3% ahead. The GTX 460 v2 is a historical artifact, not a competitive option. The recorded data shows no scenario where the NVIDIA card wins, and its only benchmark score is lower than the AMD card's lowest recorded score (8743 versus 9002). The verdict is straightforward: the AMD Radeon Pro 450 is the superior card in every measurable way.