AMD Radeon Pro W5700 vs AMD Radeon RX 590 Comparison

The AMD Radeon Pro W5700 and AMD Radeon RX 590 represent two distinct design philosophies from the same manufacturer, separated by a generation of architecture and a clear performance gulf. The W5700, built on the 7nm Navi 10 chip with RDNA 1.0 architecture, posts an average benchmark score of 25,726, placing it in the 71st percentile of all GPUs. The RX 590, using the older 12nm Polaris 30 chip with GCN 4.0 architecture, achieves an average score of 24,744, sitting just one percentile lower at 70. While the average scores appear close, the single head-to-head benchmark available reveals a decisive advantage for the W5700, which wins the only shared test by a margin of 85%. This data paints a picture of a professional-grade card that significantly outperforms its consumer predecessor in raw compute, despite the modest difference in their aggregate scores.

The Verdict

The benchmark data is unequivocal in the single metric where both cards were tested head-to-head. In the Geekbench Metal test, the AMD Radeon Pro W5700 scores 89,557, while the AMD Radeon RX 590 scores 48,407. This represents an 85% advantage for the W5700, a massive performance gap that dwarfs any other comparison between the two cards. For any workload that leverages the Metal API, the W5700 is the clear choice based on this data alone. The W5700’s nearest rivals in terms of average score include the NVIDIA GeForce RTX 3080 Ti Mobile at 25,740 (0.1% ahead) and the AMD Radeon RX 6700M at 25,633 (0.4% behind), indicating it competes with high-end mobile parts. The RX 590, meanwhile, sits near the NVIDIA RTX A5000 Mobile (24,763, 0.1% ahead) and the Intel Arc A350M (24,647, 0.4% behind), a lower tier of competition.

The W5700 is positioned for users who prioritize compute performance and professional application support, evidenced by its RDNA 1.0 architecture, 41.0M transistors per mm² density, and 8.663 TFLOPS FP32 throughput. Its 10,300 million transistors on a 251 mm² die deliver a texture rate of 270.7 GTexel/s and a pixel rate of 120.3 GPixel/s, figures that are substantially higher than the RX 590’s 222.5 GTexel/s and 49.44 GPixel/s. The RX 590, with its lower 7.119 TFLOPS FP32 performance and 5,700 million transistors on a 232 mm² die, is the more modest performer. Its only bright spot is its lower 175W TDP compared to the W5700’s 205W, but this does not compensate for the performance deficit. The data suggests the W5700 is the superior product for any task requiring graphics compute, while the RX 590 offers a lower-performance alternative with a lower power draw.

Where Each One Wins

Based on the available benchmark results, the AMD Radeon Pro W5700 wins the only head-to-head test, the Geekbench Metal benchmark, by a wide margin. This is the sole comparative data point, and it favors the W5700 overwhelmingly. There are no benchmark results in the head-to-head set where the RX 590 emerges victorious, as the wins tally shows one win for the W5700 and zero for the RX 590. This suggests that in the specific workload represented by Geekbench Metal, which typically stresses GPU compute and graphics rendering, the W5700’s architectural advantages are decisive.

The RX 590’s case for selection rests on its lower power requirements. With a TDP of 175W and a suggested PSU of 450W, it is less demanding on system power delivery compared to the W5700’s 205W TDP and 550W suggested PSU. The RX 590 also uses a single 8-pin power connector, whereas the W5700 requires a 1x 6-pin plus 1x 8-pin configuration. For systems with limited power capacity or older power supplies, the RX 590 is the more feasible option from a power perspective. However, this is a practical consideration rather than a performance win. The W5700 also supports PCIe 4.0 x16, while the RX 590 is limited to PCIe 3.0 x16, which may offer bandwidth advantages in certain data-transfer-heavy scenarios for the W5700.

Head-to-Head Benchmarks

The only direct comparison available is the Geekbench Metal test, and the results are stark. The AMD Radeon Pro W5700 scores 89,557, while the AMD Radeon RX 590 scores 48,407. The W5700 wins this test with a delta of 85%. This means the W5700 delivers nearly double the performance of the RX 590 in this specific benchmark. To put this in context, the W5700’s score of 89,557 would position it far ahead of its nearest rivals in average score, such as the AMD FirePro D700 at 25,842 or the NVIDIA GeForce RTX 3080 Ti Mobile at 25,740, though those are different benchmark suites.

For the RX 590, its only other benchmark results are a 3DMark Steel Nomad DX12 score of 1,081 and the Geekbench Metal score of 48,407. The W5700 has no comparable 3DMark result in the data, so no direct comparison can be made on that test. The W5700’s Geekbench OpenCL score is 74,613, and its Vulkan score is 70,706, though the RX 590 has no corresponding OpenCL or Vulkan scores in the head-to-head data. The 85% delta in Metal performance is the definitive metric for comparing these two cards, showing a clear and substantial victory for the W5700. In comparison, the W5700’s average score of 25,726 is only 4% higher than the RX 590’s 24,744, but this aggregate figure masks the massive single-test disparity.

FAQ

Q: Which GPU is faster in the Geekbench Metal benchmark?

A: The AMD Radeon Pro W5700 is significantly faster, scoring 89,557 compared to the RX 590’s 48,407, a difference of 85%.

Q: How do their average benchmark scores compare?

A: The W5700 has an average benchmark score of 25,726, while the RX 590 scores 24,744. This puts the W5700 in the 71st percentile of all GPUs, with the RX 590 in the 70th.

Q: What are the power consumption differences?

A: The RX 590 has a lower TDP of 175W and a suggested PSU of 450W, while the W5700 has a TDP of 205W and a suggested PSU of 550W.

Q: Which card has higher memory bandwidth?

A: The W5700 offers 448.0 GB/s of bandwidth with GDDR6 memory, whereas the RX 590 provides 256.0 GB/s with GDDR5 memory.

Q: Are there any benchmark tests where the RX 590 wins?

A: No. In the head-to-head benchmark data, the W5700 wins the only shared test (Geekbench Metal), and there are no tests where the RX 590 is victorious.

Q: What is the transistor density of each chip?

A: The W5700’s Navi 10 chip has a transistor density of 41.0M per mm², while the RX 590’s Polaris 30 chip has a density of 24.6M per mm².

Architecture Differences

The two cards are built on fundamentally different architectures. The AMD Radeon Pro W5700 uses the Navi 10 chip with RDNA 1.0 architecture, fabricated on a 7nm process at TSMC. This chip contains 10,300 million transistors on a 251 mm² die. The RX 590, in contrast, uses the Polaris 30 chip with the older GCN 4.0 architecture, built on a 12nm process at GlobalFoundries, with 5,700 million transistors on a 232 mm² die. The W5700’s architecture is newer and denser, with a transistor density of 41.0M per mm² versus the RX 590’s 24.6M per mm².

Core configurations show both cards feature 2304 shading units and 144 texture mapping units, but they diverge on render output units. The W5700 has 64 ROPs, while the RX 590 has only 32. This contributes to the W5700’s pixel rate of 120.3 GPixel/s, more than double the RX 590’s 49.44 GPixel/s. The texture rates also differ, with the W5700 at 270.7 GTexel/s and the RX 590 at 222.5 GTexel/s. Compute performance follows the same pattern: the W5700 delivers 8.663 TFLOPS of FP32 and 17.33 TFLOPS of FP16 (2:1 ratio), while the RX 590 provides 7.119 TFLOPS of both FP32 and FP16 (1:1 ratio).

Memory subsystems are another differentiator. The W5700 uses 8 GB of GDDR6 memory on a 256-bit bus, achieving 448.0 GB/s bandwidth with a memory clock of 1750 MHz (14 Gbps effective). The RX 590 uses 8 GB of GDDR5 memory on a 256-bit bus, reaching only 256.0 GB/s with a 2000 MHz clock (8 Gbps effective). The W5700 also supports PCIe 4.0 x16, while the RX 590 is limited to PCIe 3.0 x16. In terms of display outputs, the W5700 offers 5x mini-DisplayPort 1.4a and 1x USB Type-C, whereas the RX 590 provides 1x HDMI 2.0b and 3x DisplayPort 1.4a. The W5700 supports DirectX 12 (12_1) and Vulkan 1.4, while the RX 590 supports DirectX 12 (12_0) and Vulkan 1.3, with both offering OpenGL 4.6.