AMD Radeon Pro 460 vs NVIDIA GeForce GTX 770 Comparison

Head-to-Head Benchmarks

The benchmark data reveals a starkly split picture between these two graphics cards. The AMD Radeon Pro 460 and the NVIDIA GeForce GTX 770 each dominate in different API tests, and the margins tell a clear story about their respective strengths.

The most dramatic result comes from the Geekbench Metal test. Here, the AMD Radeon Pro 460 scores 20,426 points, which is a staggering 118% higher than the 9,369 points posted by the NVIDIA GeForce GTX 770. This is not a small edge; it is a complete rout. The AMD card is more than twice as fast in this particular workload, reflecting its modern architecture's strong support for Apple's Metal API. For anyone running Metal-based applications, the Radeon Pro 460 is the definitive choice based on this measurement alone.

However, the tables turn when looking at OpenCL performance. The GeForce GTX 770 edges out the Radeon Pro 460 with a score of 15,707 compared to 15,284. The delta is only 2.7% in favor of NVIDIA, which puts this result within the margin of typical run-to-run variance. In practical terms, these two cards are effectively tied in OpenCL compute workloads. The data shows a narrow win for the GTX 770, but the gap is small enough that real-world applications would likely show no consistent advantage for either card.

The Vulkan test produces a more decisive NVIDIA victory. The GTX 770 scores 19,166 points, while the Radeon Pro 460 manages 16,816 points. This represents a 12.3% advantage for the NVIDIA card. Vulkan is a cross-platform graphics and compute API, and here the older Kepler architecture demonstrates that it still has significant compute throughput to offer. The GTX 770's higher raw shading unit count and memory bandwidth likely contribute to this lead.

Counting the wins, the NVIDIA card takes two of the three head-to-head tests, while the AMD card claims one, albeit with a much larger margin. The average benchmark scores reflect this split. The Radeon Pro 460 has an average score of 17,509 across all its benchmark results, while the GTX 770 averages 14,747 points. The AMD card's overall average is higher because its massive Metal win offsets the narrower losses in OpenCL and Vulkan.

Looking at percentile rankings, the Radeon Pro 460 sits at the 61st percentile among all GPUs, while the GTX 770 sits at the 57th percentile. Both cards are solidly mid-pack, but the AMD part holds a slight overall edge. The nearest rivals for the Radeon Pro 460 include the NVIDIA Tesla K40c at 17,468 points (0.2% behind), the AMD Radeon Pro 560 at 17,551 points (0.2% ahead), and the AMD Radeon 780M at 17,588 points (0.5% ahead). The GTX 770's closest competitors include the AMD Radeon RX 5500 XT at 14,692 points (0.4% behind) and the NVIDIA Quadro M2000 at 14,532 points (1.5% behind).

FAQ

Q: Which card is faster in Metal benchmarks?

A: The AMD Radeon Pro 460 is dramatically faster in Geekbench Metal, scoring 20,426 points versus 9,369 points for the NVIDIA GeForce GTX 770. This is a 118% advantage for the AMD card.

Q: How do the cards compare in OpenCL performance?

A: The NVIDIA GeForce GTX 770 edges out the AMD Radeon Pro 460 in OpenCL, scoring 15,707 versus 15,284 points. The difference is only 2.7%, making this effectively a tie in practical use.

Q: Which GPU wins in Vulkan workloads?

A: The NVIDIA GeForce GTX 770 takes the Vulkan test with 19,166 points against 16,816 points for the AMD Radeon Pro 460, a 12.3% lead for NVIDIA.

Q: What is the overall average benchmark score for each card?

A: The AMD Radeon Pro 460 has an average benchmark score of 17,509 points, while the NVIDIA GeForce GTX 770 averages 14,747 points. The AMD card holds a higher overall average due to its dominant Metal result.

Q: How do their percentile rankings compare?

A: The AMD Radeon Pro 460 sits at the 61st percentile among all GPUs, while the NVIDIA GeForce GTX 770 sits at the 57th percentile. Both are mid-range performers, but the AMD card ranks slightly higher.

Q: Which card has a higher transistor density?

A: The AMD Radeon Pro 460 has a transistor density of 24.4 million transistors per square millimeter, compared to 12.0 million for the NVIDIA GeForce GTX 770. This reflects the AMD card's newer 14nm manufacturing process versus the 28nm process used for the GTX 770.

Architecture Differences

The architectural gap between these two GPUs is substantial, reflecting their different release periods and design goals. The AMD Radeon Pro 460 is built on the Baffin chip using the GCN 4.0 architecture, fabricated on a 14nm process at GlobalFoundries. The NVIDIA GeForce GTX 770 uses the GK104 chip with the Kepler architecture, manufactured on a 28nm process at TSMC. This process node difference is significant: 14nm versus 28nm allows the AMD chip to pack transistors much more densely.

The numbers for transistor density are stark. The AMD chip has 3,000 million transistors on a die size of 123 square millimeters, yielding a density of 24.4 million transistors per square millimeter. The NVIDIA chip has 3,540 million transistors on a much larger die of 294 square millimeters, giving a density of only 12.0 million per square millimeter. The AMD chip is smaller and denser, which is a direct benefit of the newer manufacturing process.

Memory configurations also differ fundamentally. The Radeon Pro 460 uses 4 GB of GDDR5 memory on a 128-bit bus, providing 81.28 GB/s of bandwidth. The GTX 770 uses 2 GB of GDDR5 memory on a 256-bit bus, delivering 224.4 GB/s of bandwidth. The NVIDIA card has significantly more memory bandwidth, more than 2.7 times that of the AMD card, which helps explain its strong Vulkan and OpenCL performance despite being older.

Compute resources are distributed differently as well. The Radeon Pro 460 has 1,024 shading units, 64 texture mapping units (TMUs), and 16 raster operation units (ROPs). The GTX 770 has 1,536 shading units, 128 TMUs, and 32 ROPs. The NVIDIA card has 50% more shading units, twice the TMUs, and twice the ROPs. This raw resource advantage shows up in its higher pixel rate (34.72 GPixel/s versus 14.51 GPixel/s) and texture rate (138.9 GTexel/s versus 58.05 GTexel/s).

The AMD card does lead in floating-point performance per watt, though both cards have notable FP32 numbers. The Radeon Pro 460 delivers 1.858 TFLOPS of FP32 performance, while the GTX 770 delivers 3.333 TFLOPS. The NVIDIA card is clearly more powerful in raw compute, but it consumes far more power to achieve that. The Radeon Pro 460 supports FP16 at a 1:1 ratio with FP32, while the GTX 770 has no listed FP16 capability.

API support also differs. The Radeon Pro 460 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. The GTX 770 supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The AMD card has a newer Vulkan version and a higher DirectX feature level. The power requirements are radically different: the Radeon Pro 460 has a TDP of 35 watts and needs no power connectors, while the GTX 770 has a 230 watt TDP and requires both a 6-pin and an 8-pin power connector, along with a 550 watt suggested power supply.

The Verdict

The data points to a clear split based on workload and platform. For Apple-centric environments that rely on Metal, the AMD Radeon Pro 460 is the overwhelming winner. Its 118% lead in the Geekbench Metal test is not just a marginal advantage; it is a category-defining difference. Anyone running Metal applications should choose the AMD card without hesitation based on these measurements.

For cross-platform compute and graphics workloads using OpenCL or Vulkan, the NVIDIA GeForce GTX 770 holds the edge. Its 2.7% lead in OpenCL is small, but its 12.3% lead in Vulkan is more meaningful. The GTX 770 also offers significantly higher raw memory bandwidth and double the shading units, TMUs, and ROPs of the AMD card. In scenarios where the API is not Metal, the NVIDIA card is the stronger performer.

However, the form factor and power envelope tell a different story. The Radeon Pro 460 is an integrated graphics processor (IGP) with a 35 watt TDP, no power connectors, and portable-device-dependent display outputs. The GTX 770 is a dual-slot card measuring 267 mm in length, 111 mm in height, and 38 mm in width, requiring a 550 watt power supply. These are not interchangeable products. The AMD card is designed for portable or compact systems, while the NVIDIA card requires a full desktop chassis with substantial power delivery.

The overall average benchmark score favors the AMD card at 17,509 points versus 14,747 points for the NVIDIA card. This is driven almost entirely by the Metal result. In neutral APIs, the NVIDIA card is competitive or superior. The choice ultimately depends on the software ecosystem. If Metal is the primary API, the Radeon Pro 460 is the clear pick. If Vulkan or OpenCL dominates, the GTX 770 offers better performance, provided the system can accommodate its power and size requirements.

Specification Differences

The two cards differ across nearly every specification field. The AMD Radeon Pro 460 is built on a 14nm process at GlobalFoundries, while the NVIDIA GeForce GTX 770 uses a 28nm process at TSMC. The AMD chip has 3,000 million transistors on a 123 square millimeter die, while the NVIDIA chip has 3,540 million transistors on a 294 square millimeter die. Transistor density is 24.4 million per square millimeter for AMD and 12.0 million for NVIDIA.

Clock speeds differ: the Radeon Pro 460 runs at 850 MHz base and 907 MHz boost, while the GTX 770 runs at 1046 MHz base and 1085 MHz boost. Memory clocks are 1270 MHz (5.1 Gbps effective) for AMD and 1753 MHz (7 Gbps effective) for NVIDIA. Memory capacity is 4 GB versus 2 GB, with bus widths of 128-bit versus 256-bit. Bandwidth is 81.28 GB/s for AMD and 224.4 GB/s for NVIDIA.

Compute units differ: the Radeon Pro 460 has 1,024 shading units, 64 TMUs, and 16 ROPs. The GTX 770 has 1,536 shading units, 128 TMUs, and 32 ROPs. Pixel rates are 14.51 GPixel/s versus 34.72 GPixel/s, and texture rates are 58.05 GTexel/s versus 138.9 GTexel/s. FP32 performance is 1.858 TFLOPS for AMD and 3.333 TFLOPS for NVIDIA, with FP16 supported at 1:1 only on the AMD card.

Power and physical specifications are vastly different. The Radeon Pro 460 has a 35 watt TDP, is an IGP form factor, and requires no power connectors. The GTX 770 has a 230 watt TDP, is dual-slot, and requires a 6-pin plus 8-pin power connector with a 550 watt suggested power supply. The bus interface is PCIe 3.0 x8 for AMD and PCIe 3.0 x16 for NVIDIA. Display outputs are portable-device-dependent for AMD, while NVIDIA provides 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2. API support includes DirectX 12 (12_0) for AMD versus DirectX 12 (11_0) for NVIDIA, and Vulkan 1.3 versus Vulkan 1.2.175. The GTX 770 has a launch MSRP of 399 USD.