AMD Radeon Pro 460 vs NVIDIA GeForce GTX 690 Comparison

AMD Radeon Pro 460 and NVIDIA GeForce GTX 690 represent two very different approaches to GPU design, separated by four years of architectural evolution and targeting entirely different use cases within the benchmark database. The data shows these are closely matched in aggregate performance, with the AMD Radeon Pro 460 scoring an average benchmark score of 17,509 against the NVIDIA GeForce GTX 690’s 17,037, a difference of roughly 2.8%. However, the underlying specifications, power characteristics, and individual benchmark results reveal stark contrasts that define their respective positions in the market.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon Pro 460 leads with an average benchmark score of 17,509, while the NVIDIA GeForce GTX 690 trails at 17,037. This places the AMD part at the 61st percentile of all GPUs, one percentile point above the GTX 690’s 60th percentile.

Q: How do the two GPUs compare in the Geekbench OpenCL test?

A: The NVIDIA GeForce GTX 690 wins the Geekbench OpenCL benchmark with a score of 17,399 against the AMD Radeon Pro 460’s 15,284, representing a 12.2% advantage for the NVIDIA card in this compute workload.

Q: What is the result of the Geekbench Vulkan benchmark?

A: The AMD Radeon Pro 460 takes the Vulkan test with a score of 16,816 versus the NVIDIA GeForce GTX 690’s 16,675, a narrow 0.8% margin that falls well within typical run-to-run variance.

Q: Which GPU consumes more power according to the specification data?

A: The NVIDIA GeForce GTX 690 has a TDP of 300 W and requires two 8-pin power connectors with a suggested 700 W power supply. The AMD Radeon Pro 460, by contrast, is rated at just 35 W and uses no external power connectors, being an integrated graphics solution on the motherboard.

Q: What are the memory configurations of these two GPUs?

A: The AMD Radeon Pro 460 comes with 4 GB of GDDR5 memory on a 128-bit bus, delivering 81.28 GB/s of bandwidth. The NVIDIA GeForce GTX 690 offers 2 GB of GDDR5 on a wider 256-bit bus, achieving 192.3 GB/s.

Q: Which GPU has the higher transistor count and larger die?

A: The NVIDIA GeForce GTX 690 packs 3,540 million transistors on a 294 mm² die using TSMC’s 28 nm process. The AMD Radeon Pro 460 has 3,000 million transistors on a much smaller 123 mm² die built on GlobalFoundries’ 14 nm node.

Architecture Differences

The architectural gap between these two GPUs is substantial, reflecting a generational shift in design philosophy. The AMD Radeon Pro 460 is built on GCN 4.0 architecture using a 14 nm process at GlobalFoundries, while the NVIDIA GeForce GTX 690 uses the older Kepler architecture on a 28 nm process from TSMC. This process advantage is immediately visible in transistor density: the AMD chip achieves 24.4 million transistors per square millimeter versus just 12.0 million for the NVIDIA part, allowing the Radeon Pro 460 to fit 3,000 million transistors into a 123 mm² die compared to the GTX 690’s 3,540 million transistors spread across 294 mm².

The two GPUs also differ fundamentally in their compute structure. The AMD Radeon Pro 460 features 1,024 shading units, 64 texture mapping units, and 16 raster operation pipelines. The NVIDIA GeForce GTX 690 counters with 1,536 shading units, 128 TMUs, and 32 ROPs, giving it a substantial theoretical throughput advantage in raw pixel and texture processing. This is reflected in the pixel rate of 32.61 GPixel/s and texture rate of 130.4 GTexel/s for the GTX 690, versus 14.51 GPixel/s and 58.05 GTexel/s for the Radeon Pro 460. The FP32 compute figures follow the same pattern: 3.130 TFLOPS for NVIDIA versus 1.858 TFLOPS for AMD, though the Radeon Pro 460 matches its FP32 rate at 1.858 TFLOPS for FP16 while the GTX 690 has no listed FP16 capability.

Memory architecture represents another sharp divergence. The GTX 690 uses a 256-bit memory bus with 2 GB of GDDR5 clocked at 6 Gbps effective, yielding 192.3 GB/s of bandwidth. The Radeon Pro 460 uses a narrower 128-bit bus but compensates with 4 GB of GDDR5 at 5.1 Gbps effective, though this only produces 81.28 GB/s. The AMD card’s larger capacity is notable for its intended use case, while the NVIDIA card’s raw bandwidth advantage is substantial. API support also differs: the Radeon Pro 460 supports DirectX 12 (12_0) and Vulkan 1.3, while the GTX 690 only reaches DirectX 12 (11_0) and Vulkan 1.2.175, with both offering OpenGL 4.6.

Head-to-Head Benchmarks

The benchmark results tell a story of two GPUs that trade blows depending on the workload, with each securing one victory in the two available tests. The NVIDIA GeForce GTX 690 dominates the Geekbench OpenCL benchmark, scoring 17,399 against the AMD Radeon Pro 460’s 15,284. This 12.2% margin is significant and aligns with the GTX 690’s higher compute hardware — more shading units, more TMUs, more ROPs, and over 1.2 TFLOPS of additional FP32 throughput. The OpenCL result is a clear case of raw hardware muscle overcoming architectural efficiency.

The AMD Radeon Pro 460 answers back in the Geekbench Vulkan benchmark, edging out the GTX 690 with a score of 16,816 versus 16,675. The 0.8% delta is marginal — within the noise of typical benchmark variance — but it does demonstrate that the newer GCN 4.0 architecture with Vulkan 1.3 support can hold its own against the older Kepler part with Vulkan 1.2.175. Notably, the AMD card’s Vulkan score is actually higher than its OpenCL score by 1,532 points, while the GTX 690’s Vulkan score is 724 points lower than its OpenCL result. This pattern suggests the Radeon Pro 460 benefits more from modern API implementations, while the GTX 690’s strengths lie in legacy compute paths.

Looking at the average benchmark scores, the AMD Radeon Pro 460’s 17,509 average is 2.8% higher than the GTX 690’s 17,037, even though the GTX 690 won the only directly comparable OpenCL test by a wide margin. The AMD card’s higher average is driven by its additional Geekbench Metal score of 20,426, a benchmark the GTX 690 does not participate in, presumably due to platform limitations on the NVIDIA side.

The Verdict

The data presents a clear split: the NVIDIA GeForce GTX 690 is the superior performer in raw compute throughput, particularly in OpenCL, where its 12.2% lead is decisive. Its 3.130 TFLOPS FP32 performance, 192.3 GB/s memory bandwidth, and higher pixel and texture rates make it the stronger choice for compute-heavy workloads that can utilize its wider memory bus and additional execution resources. The GTX 690 also carries the pedigree of a 999 USD launch MSRP, positioning it as a high-end part from its era.

The AMD Radeon Pro 460, however, offers a more modern and efficient package. Its 35 W TDP versus the GTX 690’s 300 W represents an 88% reduction in power draw, and its integrated graphics form factor eliminates the need for external power connectors or a dual-slot cooler. The 4 GB memory capacity doubles the GTX 690’s 2 GB, which matters for memory-intensive workloads despite the lower bandwidth. In Vulkan, the Radeon Pro 460 matches or slightly exceeds the GTX 690, and its Metal score of 20,426 indicates strong performance in Apple’s compute ecosystem — a domain where the GTX 690 has no presence. The Radeon Pro 460 also sits at the 61st percentile versus the GTX 690’s 60th, and its nearest rivals include the NVIDIA GeForce RTX 4060 at just 0.7% higher average score, suggesting the AMD part remains competitive against much newer hardware.

For users prioritizing raw compute throughput, particularly in OpenCL-based applications, the GTX 690 is the data-backed choice. For those needing power efficiency, larger memory capacity, modern API support, or Metal compatibility, the Radeon Pro 460 is the stronger option. Given that both GPUs are end-of-life products, the decision ultimately hinges on workload requirements rather than future-proofing.

Specification Differences

The two GPUs diverge across nearly every specification category. The AMD Radeon Pro 460 uses a 14 nm process at GlobalFoundries with 3,000 million transistors on a 123 mm² die, while the NVIDIA GeForce GTX 690 uses 28 nm at TSMC with 3,540 million transistors on a 294 mm² die. Clock speeds favor NVIDIA: 915 MHz base and 1019 MHz boost versus 850 MHz base and 907 MHz boost for the AMD part. Memory differs in size (4 GB versus 2 GB), bus width (128-bit versus 256-bit), and bandwidth (81.28 GB/s versus 192.3 GB/s). The GTX 690 has more shading units (1,536 versus 1,024), TMUs (128 versus 64), and ROPs (32 versus 16). Power consumption is dramatically different at 35 W versus 300 W, with the Radeon Pro 460 being an integrated GPU with no power connectors and the GTX 690 requiring dual 8-pin connectors and a 700 W power supply. The PCIe interface also differs: PCIe 3.0 x8 for AMD versus PCIe 3.0 x16 for NVIDIA. Display outputs differ, with the GTX 690 offering 3x DVI and 1x mini-DisplayPort while the Radeon Pro 460’s outputs are portable device dependent. The GTX 690 has physical dimensions of 279 mm length, 111 mm height, and 38 mm width, while the Radeon Pro 460 has no listed dimensions. API support shows the AMD part with DirectX 12 (12_0) and Vulkan 1.3 versus DirectX 12 (11_0) and Vulkan 1.2.175 for NVIDIA. The GTX 690’s launch MSRP was 999 USD.