AMD Radeon Pro WX 5100 vs NVIDIA GeForce GTX 760 Comparison

# AMD Radeon Pro WX 5100 vs. NVIDIA GeForce GTX 760

The AMD Radeon Pro WX 5100 and NVIDIA GeForce GTX 760 occupy different ends of the GPU spectrum despite both being end-of-life products. The data shows a clear generational and architectural divide: the WX 5100, built on GlobalFoundries' 14 nm process with GCN 4.0, delivers dramatically higher compute throughput, while the GTX 760, on TSMC's 28 nm node with Kepler, offers a lower average benchmark score but holds its own in specific legacy scenarios. Across all three shared benchmark tests, the AMD card wins outright, yet the GTX 760's average score of 9,458 slightly edges out the WX 5100's 8,863 due to the inclusion of additional DirectX and compute tests in the latter's benchmark suite.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 760 has a higher average benchmark score of 9,458 compared to the AMD Radeon Pro WX 5100's 8,863. This places the GTX 760 at the 46th percentile among all GPUs, while the WX 5100 sits at the 44th percentile.

Q: How do the two compare in Geekbench Metal performance?

A: The AMD Radeon Pro WX 5100 dominates the Geekbench Metal test, scoring 29,003 versus the GTX 760's 4,524. This represents an 84.4% advantage for the AMD card, the largest margin across any shared benchmark.

Q: Which card has more video memory?

A: The AMD Radeon Pro WX 5100 ships with 8 GB of GDDR5 memory, while the NVIDIA GeForce GTX 760 has only 2 GB. Despite the larger capacity, the WX 5100's memory bandwidth is 160.0 GB/s, which is lower than the GTX 760's 192.3 GB/s.

Q: What are the power requirements for each card?

A: The AMD Radeon Pro WX 5100 has a 75 W TDP and requires no power connectors, with a suggested 250 W power supply. The NVIDIA GeForce GTX 760 has a 170 W TDP, needs two 6-pin power connectors, and a suggested 450 W power supply.

Q: Which GPU supports newer API versions?

A: The AMD Radeon Pro WX 5100 supports DirectX 12 (12_0) and Vulkan 1.3, while the NVIDIA GeForce GTX 760 only reaches DirectX 12 (11_0) and Vulkan 1.2.175. Both cards support OpenGL 4.6.

Q: Was there a significant difference in launch pricing?

A: Yes, the AMD Radeon Pro WX 5100 had a launch MSRP of 499 USD, twice the GTX 760's launch MSRP of 249 USD. This reflects their different target markets, with the WX 5100 aimed at professional workloads.

Architecture Differences

The two GPUs come from fundamentally different architectural eras. The NVIDIA GeForce GTX 760 uses the GK104 chip based on the Kepler architecture, fabricated on a 28 nm process at TSMC. This older design integrates 3,540 million transistors on a 294 mm² die, yielding a transistor density of 12.0 million transistors per square millimeter. In contrast, the AMD Radeon Pro WX 5100 employs the Ellesmere chip with GCN 4.0 architecture, built on GlobalFoundries' 14 nm process. It packs 5,700 million transistors into a smaller 232 mm² die, achieving a much higher density of 24.6 million transistors per square millimeter.

The compute resources differ substantially. The GTX 760 features 1,152 shading units, 96 texture mapping units, and 32 ROPs. The WX 5100 significantly increases these counts to 1,792 shading units, 112 TMUs, and 32 ROPs. This translates into higher theoretical peak rates: the WX 5100 reaches 3.892 TFLOPS of FP32 performance and an identical 3.892 TFLOPS of FP16 (at a 1:1 ratio), whereas the GTX 760 peaks at 2.378 TFLOPS FP32 with no FP16 capability listed. Pixel and texture fill rates also favor the AMD card, with 34.75 GPixel/s and 121.6 GTexel/s versus 24.77 GPixel/s and 99.07 GTexel/s respectively.

Memory architectures share a 256-bit bus width, but capacities diverge widely. The GTX 760 comes with 2 GB of GDDR5 clocked at 1502 MHz (6 Gbps effective), delivering 192.3 GB/s of bandwidth. The WX 5100 offers 8 GB of GDDR5 at 1250 MHz (5 Gbps effective), yet its bandwidth is lower at 160.0 GB/s. Clock speeds also differ: the GTX 760 has a base clock of 980 MHz and boost of 1032 MHz, while the WX 5100 starts at a lower 713 MHz base but boosts to a higher 1086 MHz.

Where Each One Wins

The AMD Radeon Pro WX 5100 wins decisively in all three benchmark tests shared with the GTX 760. In Geekbench Metal, it scores 29,003 versus 4,524, a gap of 84.4%. In Geekbench OpenCL, the WX 5100's 24,217 outpaces the GTX 760's 11,299 by 53.3%. Similarly, in Geekbench Vulkan, the AMD card scores 26,909 against 12,551, a 53.4% advantage. These results point to the WX 5100 being the clear choice for compute-heavy applications, particularly those leveraging Metal, OpenCL, or Vulkan APIs. Its higher shading unit count, larger memory pool, and superior FP32 throughput align with professional rendering and general-purpose GPU workloads.

The NVIDIA GeForce GTX 760, despite losing every head-to-head comparison, still has niches where it holds advantages. Its higher memory bandwidth of 192.3 GB/s, compared to the WX 5100's 160.0 GB/s, could benefit bandwidth-sensitive tasks. The GTX 760 also has a higher average benchmark score overall, driven by additional tests in its suite (though the WX 5100 has more tests recorded overall, including DirectX and compute benchmarks). The older Kepler architecture supports DirectX 12 (11_0), which may be sufficient for legacy applications. Its lower launch MSRP of 249 USD also indicates a more accessible entry point historically.

Specification Differences

The two cards diverge across nearly every specification category. Process technology differs: the GTX 760 uses 28 nm TSMC, while the WX 5100 uses 14 nm GlobalFoundries. Transistor counts favor AMD (5,700 million vs. 3,540 million), but die size favors NVIDIA (294 mm² vs. 232 mm²). Clock speeds show NVIDIA with a higher base (980 MHz vs. 713 MHz) but AMD with a higher boost (1086 MHz vs. 1032 MHz). Memory capacity strongly favors AMD (8 GB vs. 2 GB), as does bandwidth efficiency per watt, though NVIDIA retains the raw bandwidth crown (192.3 GB/s vs. 160.0 GB/s).

Power and physical specifications tell a story of differing design priorities. The WX 5100 draws only 75 W with no external power connectors, fitting a single-slot, 173 mm (6.8 inches) long, 112 mm (4.4 inches) high profile. The GTX 760 requires 170 W, two 6-pin connectors, a dual-slot cooler, and measures 241 mm (9.5 inches) long. Display outputs also differ: the WX 5100 offers four DisplayPort 1.4a connections, while the GTX 760 provides two DVI, one HDMI 1.4a, and one DisplayPort 1.2. API support favors AMD with DirectX 12 (12_0) and Vulkan 1.3 versus NVIDIA's DirectX 12 (11_0) and Vulkan 1.2.175.

Head-to-Head Benchmarks

The Geekbench Metal test produces the most lopsided result. The AMD Radeon Pro WX 5100 scores 29,003, while the NVIDIA GeForce GTX 760 manages only 4,524. This 84.4% deficit for NVIDIA suggests that the Kepler architecture is severely disadvantaged in Apple's Metal API, likely due to its age and lack of modern feature support. The WX 5100's GCN 4.0 architecture, with its 1,792 shading units, appears far better optimized for Metal workloads.

Geekbench OpenCL shows a similar but less extreme pattern. The WX 5100 scores 24,217 against the GTX 760's 11,299, a 53.3% difference. This aligns closely with the theoretical FP32 compute gap: the AMD card offers 3.892 TFLOPS versus 2.378 TFLOPS for NVIDIA, a 63.7% advantage in raw throughput. The actual benchmark delta is slightly smaller, indicating some efficiency differences in how each architecture utilizes its compute units.

Geekbench Vulkan results mirror OpenCL closely. The WX 5100 achieves 26,909, while the GTX 760 reaches 12,551, another 53.4% margin. This consistency across OpenCL and Vulkan suggests the WX 5100's advantage is fundamental to its architecture rather than API-specific. The GTX 760's Vulkan support (version 1.2.175) is older than the WX 5100's (version 1.3), which may contribute to its lower performance in this modern API.

The Verdict

The data overwhelmingly favors the AMD Radeon Pro WX 5100 in raw performance. It wins all three head-to-head benchmarks, with margins ranging from 53.3% to 84.4%. Its 8 GB memory capacity, higher shading unit count, and doubled FP32 throughput make it the superior choice for compute-intensive applications, professional workloads, and modern API support. The WX 5100 also offers practical advantages: a single-slot design, no power connectors, and a 75 W TDP that simplifies system integration compared to the GTX 760's dual-slot, 170 W requirement.

However, the NVIDIA GeForce GTX 760 should not be dismissed entirely. Its average benchmark score of 9,458 exceeds the WX 5100's 8,863, placing it in the 46th percentile versus the 44th. This suggests that in legacy DirectX tests (which the WX 5100 scores poorly on, with Passmark DirectX 9 at 88, DirectX 10 at 29, DirectX 11 at 36, and DirectX 12 at 26), the GTX 760 may perform relatively better. The GTX 760 also offers higher memory bandwidth, which could matter for specific bandwidth-bound scenarios.

For users prioritizing modern compute performance, API compatibility, and memory capacity, the AMD Radeon Pro WX 5100 is the clear winner. For those targeting older DirectX workloads or needing maximum memory bandwidth with lower historical cost, the NVIDIA GeForce GTX 760 remains a viable alternative. The WX 5100's professional positioning, evidenced by its 499 USD launch MSRP and DisplayPort 1.4a outputs, makes it the more future-proof investment despite its lower overall percentile ranking.