Intel Arc B570 vs NVIDIA GeForce GTX 1060 6 GB Comparison
Intel Arc B570
GeForce GTX 1060 6 GB
PERFORMANCE BENCHMARKS
Analysis: Intel Arc B570 vs NVIDIA GeForce GTX 1060 6 GB
The NVIDIA GeForce GTX 1060 6 GB and the Intel Arc B570 represent two distinct generations of graphics hardware, separated by nearly a decade of architectural evolution. The data shows a clear performance hierarchy, with the Intel Arc B570 delivering substantially higher raw compute and graphics throughput in shared benchmarks, while the older GTX 1060 retains a niche in legacy API compatibility and a lower system power requirement. This analysis breaks down the benchmark results, architectural differences, and specification gaps to determine where each card stands.
Where Each One Wins
The head-to-head benchmark data is unambiguous: the Intel Arc B570 wins every shared test, and by wide margins. In the Geekbench OpenCL compute test, the Arc B570 scores 83,514 against the GTX 1060’s 32,322, a delta of -61.3% from the perspective of the older card. This means the Arc B570 is roughly 2.6 times faster in raw compute throughput. The gap is even larger in the Geekbench Vulkan test, where the Arc B570 hits 96,844 versus the GTX 1060’s 18,659, a -80.7% delta — translating to over 5 times higher performance.
The GTX 1060’s wins are not in raw speed but in compatibility and efficiency. It supports DirectX 12 (12_1) and OpenGL 4.6, whereas the Arc B570 supports DirectX 12 Ultimate (12_2) and OpenGL 4.6. Both cards support Vulkan 1.4. The GTX 1060 has a TDP of 120 W and requires a 300 W suggested PSU, compared to the Arc B570’s 150 W TDP and 450 W suggested PSU. The GTX 1060 also uses a single 6-pin power connector, while the Arc B570 needs an 8-pin. For systems with older power supplies or tighter thermal envelopes, the GTX 1060 is the more accommodating choice.
Architecture Differences
The architectural gap is fundamental. The GTX 1060 uses the GP106 chip built on Pascal architecture, fabricated on TSMC’s 16 nm process. It packs 4,400 million transistors into a 200 mm² die, yielding a transistor density of 22.0M per mm². The Arc B570, in contrast, uses the BMG-G21 chip on Intel’s Xe2-HPG architecture (Battlemage generation), built on TSMC’s 5 nm process. It contains 19,600 million transistors across a 272 mm² die, achieving a density of 72.1M per mm² — over three times higher.
Core counts differ dramatically. The GTX 1060 has 1,280 shading units, 80 texture mapping units (TMUs), and 48 raster output units (ROPs). The Arc B570 has 2,304 shading units, 144 TMUs, and 80 ROPs. The Arc B570 also includes 18 ray tracing cores, a feature entirely absent from the Pascal-based GTX 1060. The GTX 1060 has no tensor cores, and the Arc B570’s tensor core count is not specified in the data.
Clock speeds favor the newer card. The GTX 1060 runs at a base of 1506 MHz and a boost of 1709 MHz. The Arc B570 runs at a flat 2500 MHz for both base and boost. Memory architecture also diverges: the GTX 1060 uses 6 GB of GDDR5 on a 192-bit bus, delivering 192.2 GB/s bandwidth. The Arc B570 uses 10 GB of GDDR6 on a 160-bit bus, achieving 380.0 GB/s bandwidth. Despite a narrower bus, the Arc B570’s faster memory (19 Gbps effective versus 8 Gbps) nearly doubles bandwidth.
The Verdict
The data points to a straightforward conclusion for most users. The Intel Arc B570 is the superior performer in every measurable benchmark shared between the two. Its OpenCL score is 158% higher, and its Vulkan score is 419% higher than the GTX 1060. It offers more memory (10 GB vs 6 GB), higher bandwidth (380.0 GB/s vs 192.2 GB/s), and more than double the FP32 throughput (11.52 TFLOPS vs 4.375 TFLOPS). The Arc B570 also brings modern features like ray tracing cores and DirectX 12 Ultimate support, which the GTX 1060 cannot offer.
The GTX 1060’s case rests on legacy value. It is end-of-life, but its 120 W TDP and 300 W PSU requirement make it a drop-in replacement for older systems without PSU upgrades. Its 1x DVI output is a plus for users with older monitors. The Arc B570, by contrast, is an active product with a 150 W TDP and 450 W PSU suggestion, plus a PCIe 4.0 x8 interface that may not be supported on older motherboards. The GTX 1060 uses PCIe 3.0 x16, which is more universally compatible with older platforms.
For a new build or a substantial upgrade, the Arc B570 is the clear choice from the data. For a budget-conscious refresh of a decade-old system with a limited PSU, the GTX 1060 remains a functional option, though its performance ceiling is far lower.
FAQ
Q: Which GPU has higher raw compute performance?
A: The Intel Arc B570. Its FP32 throughput is 11.52 TFLOPS, versus the GTX 1060’s 4.375 TFLOPS. In Geekbench OpenCL, the Arc B570 scores 83,514 against the GTX 1060’s 32,322.
Q: Does the GTX 1060 support ray tracing?
A: No. The GTX 1060 has no ray tracing cores. The Intel Arc B570 includes 18 ray tracing cores.
Q: How do the memory subsystems compare?
A: The GTX 1060 has 6 GB GDDR5 on a 192-bit bus with 192.2 GB/s bandwidth. The Arc B570 has 10 GB GDDR6 on a 160-bit bus with 380.0 GB/s bandwidth.
Q: What are the power requirements for each card?
A: The GTX 1060 has a 120 W TDP, uses a 1x 6-pin connector, and suggests a 300 W PSU. The Arc B570 has a 150 W TDP, uses a 1x 8-pin connector, and suggests a 450 W PSU.
Q: Which card supports newer display outputs?
A: The Intel Arc B570. It has 1x HDMI 2.1a and 3x DisplayPort 2.1. The GTX 1060 has 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.4a.
Q: What is the performance percentile ranking for each card?
A: The GTX 1060 ranks in the 67th percentile among all GPUs, with an average benchmark score of 21,856. The Arc B570 ranks in the 65th percentile, with an average score of 20,556.
Head-to-Head Benchmarks
The two shared benchmarks tell a stark story. In Geekbench OpenCL, the GTX 1060 scores 32,322 while the Arc B570 scores 83,514. The delta is -61.3% relative to the Arc B570, meaning the GTX 1060 achieves only 38.7% of the Arc B570’s score. This test is heavily compute-oriented, and the Arc B570’s 2,304 shading units versus 1,280, combined with a 2:1 FP16 ratio (23.04 TFLOPS vs 68.36 GFLOPS), explain the massive gap.
The Geekbench Vulkan test is even more lopsided. The GTX 1060 scores 18,659, while the Arc B570 scores 96,844 — a delta of -80.7%. The Arc B570 is over 5 times faster. Vulkan benefits from modern architecture features, including the Arc B570’s ray tracing cores and DirectX 12 Ultimate feature set. The GTX 1060’s older Pascal architecture, with its 1:64 FP16 ratio, is not designed for the compute-heavy workloads that Vulkan can leverage.
There are no benchmark tests where the GTX 1060 wins. The data records 0 wins for the GTX 1060 and 2 wins for the Arc B570. The Arc B570 also has additional benchmark data points not shared with the GTX 1060, including PassMark scores (DirectX 9: 164, DirectX 10: 65, DirectX 11: 118, DirectX 12: 72, G2D: 661, G3D: 14,195, GPU compute: 7,281) and a 3DMark Steel Nomad DX12 score of 2,649. These are not directly comparable, but they reinforce the Arc B570’s broader testing profile.
Specification Differences
The two cards differ in nearly every measurable specification. The GTX 1060 is built on a 16 nm process, while the Arc B570 uses 5 nm. Transistor counts are 4,400 million versus 19,600 million. Die sizes are 200 mm² versus 272 mm². Transistor density is 22.0M / mm² versus 72.1M / mm².
Clock speeds: the GTX 1060 runs at 1506 MHz base and 1709 MHz boost. The Arc B570 runs at 2500 MHz base and 2500 MHz boost. Memory clocks are 2002 MHz (8 Gbps effective) for the GTX 1060, versus 2375 MHz (19 Gbps effective) for the Arc B570.
Memory capacity and type: 6 GB GDDR5 for the GTX 1060, versus 10 GB GDDR6 for the Arc B570. Bus widths are 192-bit and 160-bit, respectively. Bandwidth is 192.2 GB/s versus 380.0 GB/s.
Compute units: the GTX 1060 has 1,280 shading units, 80 TMUs, and 48 ROPs. The Arc B570 has 2,304 shading units, 144 TMUs, and 80 ROPs. The Arc B570 has 18 ray tracing cores; the GTX 1060 has none.
Pixel and texture rates: the GTX 1060 achieves 82.03 GPixel/s and 136.7 GTexel/s. The Arc B570 achieves 200.0 GPixel/s and 360.0 GTexel/s. FP32 is 4.375 TFLOPS versus 11.52 TFLOPS. FP16 is 68.36 GFLOPS (1:64) versus 23.04 TFLOPS (2:1).
Power and physical specs: the GTX 1060 has a 120 W TDP, 1x 6-pin connector, and 300 W suggested PSU. The Arc B570 has a 150 W TDP, 1x 8-pin connector, and 450 W suggested PSU. The GTX 1060 measures 250 mm (9.8 inches) in length and 111 mm (4.4 inches) in height. The Arc B570 measures 272 mm (10.7 inches) in length and 115 mm (4.5 inches) in height. Both are dual-slot.
Bus interface: the GTX 1060 uses PCIe 3.0 x16, while the Arc B570 uses PCIe 4.0 x8. Display outputs: the GTX 1060 has 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.4a. The Arc B570 has 1x HDMI 2.1a and 3x DisplayPort 2.1.
API support: the GTX 1060 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The Arc B570 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.