AMD Radeon RX 5600 XT vs Intel Arc B570 Comparison
AMD Radeon RX 5600 XT
Arc B570
PERFORMANCE BENCHMARKS
Analysis: AMD Radeon RX 5600 XT vs Intel Arc B570
Head-to-Head Benchmarks
The benchmark comparison between the AMD Radeon RX 5600 XT and the Intel Arc B570 reveals a lopsided contest, with Intel claiming victory in 7 of the 10 head-to-head tests. The most dramatic gap appears in the 3DMark Steel Nomad DX12 test, where the Arc B570 scores 2649 against the RX 5600 XT’s 1669 — a 37% deficit for the AMD card. This is not a marginal difference; it signals a fundamental generational leap in raw throughput for modern DirectX 12 workloads.
The Geekbench results tell a similar story. In the Vulkan test, the Intel card posts 96844 points versus AMD’s 56218, a staggering 41.9% advantage. The OpenCL test is closer but still decisive: 83514 for Intel versus 68537 for AMD, a 17.9% gap. These numbers suggest that the Arc B570’s architecture handles compute-heavy API workloads with far greater efficiency than the older RDNA 1.0 design, particularly when the workload can exploit parallel execution across its 2304 shading units — the same count as the RX 5600 XT, yet with nearly double the FP32 throughput (11.52 TFLOPS versus 7.188 TFLOPS).
The PassMark suite offers a more nuanced picture. The DirectX 11 test shows Intel ahead by 18.6% (118 versus 96), and DirectX 12 shows a 27.8% lead (72 versus 52). The GPU Compute test adds another Intel win: 7281 versus 6296, a 13.5% margin. However, the AMD card fights back in several legacy and 2D-oriented tests. The DirectX 9 test is a clear AMD victory at 202 versus 164, a 23.2% edge. The DirectX 10 test also favors AMD, though narrowly: 73 versus 65, a 12.3% difference. Most striking is the PassMark G2D score, where AMD dominates 870 to 661 — a 31.6% lead that suggests the RX 5600 XT retains a strong advantage in 2D rendering and desktop composition tasks.
The overall PassMark G3D score, which aggregates many 3D scenarios, lands in Intel’s favor but by a modest margin: 14195 versus 13457, just 5.2% apart. This is the closest of the Intel wins, and it hints that in certain mixed workloads the two cards are nearly interchangeable. The average benchmark scores reinforce this: AMD’s average is 20713, Intel’s is 20556, a difference of only 0.8% in AMD’s favor. In fact, the nearest rival list for the RX 5600 XT places the Arc B570 at a deltaPct of 0.8 — meaning the Intel card is slightly behind on average, despite winning the majority of individual tests. This paradox arises because AMD’s wins in the G2D, DirectX 9, and DirectX 10 tests are large enough to offset Intel’s bigger wins in the compute-heavy workloads.
The Verdict
The data paints a clear picture of two cards with divergent strengths. For anyone prioritizing modern 3D gaming, ray tracing, or compute-heavy applications, the Intel Arc B570 is the superior choice. Its 3DMark Steel Nomad score is 58.7% higher, and its Vulkan score is 72.2% higher — margins that will translate into visibly smoother frame rates in current titles. The Intel card also leads in DirectX 11 and DirectX 12, which cover the vast majority of contemporary game engines.
However, the RX 5600 XT is not obsolete. Its wins in DirectX 9 (23.2% ahead), DirectX 10 (12.3% ahead), and G2D (31.6% ahead) indicate that for older software, emulated environments, or productivity tasks that rely on 2D acceleration, AMD retains a meaningful edge. The average benchmark scores are nearly identical — 20713 versus 20556 — meaning that a user who runs a diverse mix of applications might see no overall difference in daily performance.
The percentile rankings reinforce this near-tie: the RX 5600 XT sits at the 66th percentile of all GPUs, while the Arc B570 sits at the 65th. Both are within 0.8% of each other by average score. The verdict is nuanced: the Intel card is the modern performer with a clear edge in new APIs, while the AMD card is the legacy champion that still holds its own in older workloads. Neither is a universal winner; the choice hinges entirely on the software environment.
Where Each One Wins
The Intel Arc B570 claims victory in the categories that matter most for future-proofing. The 3DMark Steel Nomad DX12 test is a forward-looking benchmark for next-generation graphics, and Intel’s 37% lead there is the single largest gap in any test. The Vulkan advantage of 41.9% is equally telling, as Vulkan is increasingly the API of choice for high-performance PC games. DirectX 11 and DirectX 12 wins of 18.6% and 27.8% respectively cover the current gaming landscape, while the GPU Compute lead of 13.5% indicates better performance in physics simulation, video encoding, and other general-purpose GPU tasks.
The AMD Radeon RX 5600 XT wins in three specific areas, all of which point to legacy or non-3D contexts. The DirectX 9 score of 202 versus 164 is a 23.2% advantage, which matters for older titles that still use the DirectX 9 pipeline — a category that includes many massively popular games like older MMORPGs and indie titles. The DirectX 10 win of 12.3% is smaller but still relevant for a niche set of games from the late 2000s. The G2D score is the most dramatic AMD victory at 31.6%, indicating superior performance in 2D rendering, which is used in desktop environments, image editing, and browser compositing.
For a gamer focused on the latest AAA releases, the Arc B570 is the clear pick. For a user who runs a mix of older titles, productivity software, and desktop applications, the RX 5600 XT’s legacy strengths could make it the more balanced option — even if its overall 3D performance lags.
FAQ
Q: Which GPU has the higher average benchmark score?
A: The AMD Radeon RX 5600 XT has an average benchmark score of 20713, while the Intel Arc B570 scores 20556 — a difference of 0.8% in AMD’s favor.
Q: How large is the performance gap in the 3DMark Steel Nomad DX12 test?
A: The Intel Arc B570 scores 2649 versus the RX 5600 XT’s 1669, giving Intel a 37% lead in this modern DirectX 12 benchmark.
Q: Does the AMD card win any compute-oriented tests?
A: No. The Intel Arc B570 wins the PassMark GPU Compute test with 7281 points versus 6296, a 13.5% advantage, and also leads in Geekbench OpenCL with 83514 versus 68537.
Q: In which test does the AMD card show its largest advantage?
A: The RX 5600 XT’s biggest win is in the PassMark G2D test, where it scores 870 versus 661 — a 31.6% lead over the Arc B570.
Q: Are the two cards in the same performance percentile?
A: The RX 5600 XT is at the 66th percentile of all GPUs, while the Arc B570 is at the 65th, placing them side-by-side in overall standing.
Q: Which GPU is better for DirectX 9 games?
A: The AMD Radeon RX 5600 XT is clearly better, scoring 202 versus 164 in the PassMark DirectX 9 test, a 23.2% advantage.
Architecture Differences
The architectural divide between these two GPUs is stark. The AMD Radeon RX 5600 XT is built on the RDNA 1.0 architecture with the Navi 10 chip, fabricated on a 7 nm process at TSMC. It packs 10,300 million transistors into a 251 mm² die, yielding a transistor density of 41.0M per mm². The Intel Arc B570, in contrast, uses the Xe2-HPG architecture with the BMG-G21 chip, on a more advanced 5 nm process also from TSMC. It contains 19,600 million transistors on a 272 mm² die, achieving a much higher density of 72.1M per mm². This nearly 90% increase in transistor count, combined with the smaller process node, explains much of the Intel card’s raw compute advantage.
Both cards have 2304 shading units and 144 texture mapping units, but the Intel card has 80 ROPs versus AMD’s 64, contributing to its higher pixel rate of 200.0 GPixel/s against 99.84 GPixel/s. The Intel card also features 18 dedicated ray tracing cores, while the RX 5600 XT has none — a critical difference for modern games that use ray-traced effects. The FP32 performance tells the story: Intel’s 11.52 TFLOPS is 60% higher than AMD’s 7.188 TFLOPS, and the FP16 rate of 23.04 TFLOPS versus 14.38 TFLOPS (both at 2:1 ratio) doubles down on that lead. The Intel card’s texture rate of 360.0 GTexel/s is also far ahead of AMD’s 224.6 GTexel/s.
The memory subsystems differ as well. The RX 5600 XT uses 6 GB of GDDR6 on a 192-bit bus, delivering 288.0 GB/s of bandwidth. The Arc B570 offers 10 GB of GDDR6 on a 160-bit bus, yet achieves 380.0 GB/s bandwidth thanks to faster effective memory speeds (19 Gbps versus 12 Gbps). This bandwidth advantage is crucial for high-resolution textures and compute workloads.
Specification Differences
The two GPUs differ on several key specification fields. The RX 5600 XT has a base clock of 1130 MHz and a boost clock of 1560 MHz, with a game clock of 1375 MHz. The Arc B570 operates at a flat 2500 MHz for both base and boost clocks — a much higher frequency that contributes to its performance gains. Memory clocks also diverge: AMD runs at 1500 MHz (12 Gbps effective), while Intel runs at 2375 MHz (19 Gbps effective).
Memory capacity is a major differentiator: 6 GB versus 10 GB. The bus widths are 192-bit for AMD and 160-bit for Intel, but as noted, Intel’s higher memory speed yields greater bandwidth. The RX 5600 XT has 64 ROPs and no ray tracing cores, while the Arc B570 has 80 ROPs and 18 ray tracing cores. The production status also differs: the RX 5600 XT is end-of-life, released on 2020-01-20, while the Arc B570 is active, released on 2025-01-15.
The display outputs reflect the generational gap. AMD offers 1x HDMI 2.0b and 3x DisplayPort 1.4a, while Intel provides 1x HDMI 2.1a and 3x DisplayPort 2.1. The bus interface is PCIe 4.0 x16 for AMD but PCIe 4.0 x8 for Intel — a potential bottleneck for the Intel card in some systems, though the bandwidth requirements for a GPU of this class are typically not limiting. Physical dimensions are similar: AMD is 267 mm long (10.5 inches), Intel is 272 mm long (10.7 inches) and 115 mm tall (4.5 inches). Both are dual-slot, use a single 8-pin power connector, and have a TDP of 150 W with a suggested PSU of 450 W.