Intel Arc B580 vs NVIDIA GeForce GTX 1060 6 GB Comparison

The Intel Arc B580 and the NVIDIA GeForce GTX 1060 6 GB represent two distinct eras of GPU design, and the benchmark data reflects a generational chasm. The Arc B580 is decisively faster across every measured metric, but the GTX 1060 was a legendary card in its time. This analysis quantifies that gap using the available fact pack data, focusing on raw performance, architectural differences, and specific benchmark results.

FAQ

Q: How much faster is the Intel Arc B580 than the GTX 1060 in OpenCL compute performance?

A: The Arc B580 scores 92,821 in Geekbench OpenCL, while the GTX 1060 scores 32,322. This represents a 187.2% advantage for the Intel card, meaning it is nearly three times faster in this compute workload.

Q: Which card has a higher average benchmark score, and by how much?

A: The Intel Arc B580 has an average benchmark score of 23,021, compared to the GTX 1060's 21,856. The Arc B580 is ahead by roughly 5.3%, though the GTX 1060 sits very close in the overall percentile rankings (67th vs 68th percentile for all GPUs).

Q: What is the difference in memory bandwidth between the two cards?

A: The Arc B580 offers 456.0 GB/s of bandwidth from its 12 GB GDDR6 memory on a 192-bit bus. The GTX 1060 provides 192.2 GB/s from 6 GB of GDDR5 on the same 192-bit bus width, giving the Intel card over 2.3 times the bandwidth.

Q: Does the GTX 1060 support hardware ray tracing?

A: No. The fact pack lists no RT cores for the GTX 1060 (rtCores: null). In contrast, the Intel Arc B580 includes 20 dedicated RT cores for hardware-accelerated ray tracing.

Q: How do their Vulkan performance scores compare?

A: In Geekbench Vulkan, the Arc B580 scores 109,672, versus 18,659 for the GTX 1060. The Intel card wins by 487.8%, a massive lead that highlights the architectural advancements in the newer GPU.

Q: What are the launch MSRPs for these two cards?

A: The Intel Arc B580 had a launch MSRP of 249 USD, while the NVIDIA GeForce GTX 1060 6 GB launched with an MSRP of 299 USD.

Architecture Differences

The architectural gap between the Arc B580 and GTX 1060 is vast, spanning process technology, core design, and feature support. The Intel card is built on TSMC's 5 nm process, while the GTX 1060 uses a 16 nm node from the same foundry. This process shrink allows the Arc B580 to pack 19,600 million transistors into a 272 mm² die, yielding a density of 72.1M transistors per mm². The GTX 1060, by contrast, contains 4,400 million transistors on a 200 mm² die, with a density of just 22.0M / mm².

The core configurations are equally divergent. The Arc B580 features 2560 shading units, 160 TMUs, 80 ROPs, and 20 RT cores. The GTX 1060 offers 1280 shading units, 80 TMUs, and 48 ROPs, with no RT cores at all. This doubles the shader count and texture units, and nearly doubles the ROP count on the Intel side. The compute throughput reflects this: the Arc B580 delivers 13.67 TFLOPS FP32, roughly three times the GTX 1060's 4.375 TFLOPS. In FP16, the difference is starker still: the Arc B580 hits 27.34 TFLOPS with a 2:1 ratio, while the GTX 1060 manages only 68.36 GFLOPS with a 1:64 ratio.

Memory architecture also separates the two. Both use a 192-bit bus, but the Arc B580 pairs it with 12 GB of GDDR6 at 19 Gbps effective, achieving 456.0 GB/s. The GTX 1060 uses 6 GB of GDDR5 at 8 Gbps effective, for 192.2 GB/s. The Intel card's API support is more modern as well, with DirectX 12 Ultimate (12_2) versus the GTX 1060's DirectX 12 (12_1), though both support OpenGL 4.6 and Vulkan 1.4. The Arc B580 also features a PCIe 4.0 x8 interface, while the GTX 1060 uses PCIe 3.0 x16.

Head-to-Head Benchmarks

The direct head-to-head data shows a clean sweep for the Intel Arc B580, with two wins and zero for the GTX 1060. In Geekbench OpenCL, the Arc B580 posts 92,821 points against the GTX 1060's 32,322, a delta of 187.2%. This is not a marginal improvement; it is a near-tripling of compute performance in a synthetic workload that stresses general-purpose GPU compute.

The Geekbench Vulkan result is even more lopsided. The Arc B580 scores 109,672, while the GTX 1060 manages just 18,659, yielding a 487.8% advantage for Intel. This massive gap suggests that the Arc B580's architecture is far more efficient at handling modern graphics APIs, likely benefiting from its newer design and higher memory bandwidth. For context, the GTX 1060's Vulkan score is lower than its OpenCL score, while the Arc B580's Vulkan score is higher than its OpenCL score, indicating the Intel card scales better with the lower-overhead API.

The average benchmark scores reinforce this trend. The Arc B580 averages 23,021 across its suite, placing it in the 68th percentile of all GPUs. Its nearest rivals by average score include the AMD Radeon RX 580 2048SP at 23,061 (a -0.2% delta) and the NVIDIA GeForce RTX 2080 at 22,895 (+0.6% delta). The GTX 1060 averages 21,856, putting it in the 67th percentile, with nearest rivals like the AMD Radeon RX 5700 at 22,170 (-1.4% delta) and the NVIDIA Quadro RTX 5000 at 21,629 (+1% delta). While the percentile rankings are close, the raw head-to-head results show the Arc B580 is in a different performance class.

The Verdict

The data is unambiguous: the Intel Arc B580 is the superior performer in every benchmark category recorded. It wins both head-to-head tests by wide margins, offers more than double the memory capacity and bandwidth, and features modern architectural elements like RT cores and DirectX 12 Ultimate support that the GTX 1060 entirely lacks. The GTX 1060's only statistical advantages are its lower power draw (120 W vs 190 W TDP) and its legacy status as an end-of-life product with a smaller physical footprint at 250 mm length versus 272 mm for the Arc B580.

For users seeking maximum performance in current and future workloads, the Arc B580 is the clear choice. Its 12 GB VRAM and 456.0 GB/s bandwidth make it far more suitable for modern games and compute tasks, and its 487.8% Vulkan lead suggests it will handle new API-based titles far better. The GTX 1060, despite its historical significance, is now relegated to lower-end duties. Its 6 GB VRAM and 192.2 GB/s bandwidth are limiting factors, and its lack of RT cores means it cannot handle ray-traced content at all. The launch MSRP of 249 USD for the Arc B580 versus 299 USD for the GTX 1060 further underscores the generational improvement, though pricing is not a factor in the performance verdict. The GTX 1060 remains a capable card for older games or light workloads, but the benchmark results show that the Arc B580 is the definitive winner for anyone who prioritizes raw performance.

Specification Differences

| Specification | Intel Arc B580 | NVIDIA GeForce GTX 1060 6 GB |

|---|---|---|

| Process Node | 5 nm | 16 nm |

| Transistors | 19,600 million | 4,400 million |

| Die Size | 272 mm² | 200 mm² |

| Transistor Density | 72.1M / mm² | 22.0M / mm² |

| Base Clock | 2670 MHz | 1506 MHz |

| Boost Clock | 2670 MHz | 1709 MHz |

| Memory Clock | 2375 MHz (19 Gbps effective) | 2002 MHz (8 Gbps effective) |

| Memory Size | 12 GB | 6 GB |

| Memory Type | GDDR6 | GDDR5 |

| Memory Bandwidth | 456.0 GB/s | 192.2 GB/s |

| Shading Units | 2560 | 1280 |

| TMUs | 160 | 80 |

| ROPs | 80 | 48 |

| RT Cores | 20 | 0 |

| Pixel Rate | 213.6 GPixel/s | 82.03 GPixel/s |

| Texture Rate | 427.2 GTexel/s | 136.7 GTexel/s |

| FP32 Performance | 13.67 TFLOPS | 4.375 TFLOPS |

| FP16 Performance | 27.34 TFLOPS (2:1) | 68.36 GFLOPS (1:64) |

| TDP | 190 W | 120 W |

| Power Connectors | 1x 8-pin | 1x 6-pin |

| Suggested PSU | 450 W | 300 W |

| Bus Interface | PCIe 4.0 x8 | PCIe 3.0 x16 |

| DirectX Support | 12 Ultimate (12_2) | 12 (12_1) |

| Display Outputs | 1x HDMI 2.1a, 3x DisplayPort 2.1 | 1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.4a |

| Length | 272 mm (10.7 inches) | 250 mm (9.8 inches) |

| Height | 115 mm (4.5 inches) | 111 mm (4.4 inches) |

| Production Status | Active | End-of-life |

| Release Date | 2024-12-12 | 2016-07-18 |

| Launch MSRP | 249 USD | 299 USD |

Where Each One Wins

The Intel Arc B580 wins in every performance-oriented category. It dominates compute workloads, as shown by its 187.2% OpenCL lead and 487.8% Vulkan advantage. Its 12 GB VRAM and 456.0 GB/s bandwidth make it the pick for high-resolution gaming, texture-heavy mods, or GPU-accelerated rendering tasks. The 20 RT cores enable hardware ray tracing, a feature the GTX 1060 cannot offer. The Arc B580 also leads in raw throughput metrics: its 13.67 TFLOPS FP32 and 213.6 GPixel/s pixel rate are roughly three times and 2.6 times the GTX 1060's respective figures. For any modern workload that leverages DirectX 12 Ultimate or Vulkan, the Arc B580 is the only viable option of the two.

The NVIDIA GeForce GTX 1060 6 GB retains advantages only in efficiency and legacy compatibility. Its 120 W TDP is significantly lower than the Arc B580's 190 W, and it requires only a 300 W suggested PSU versus 450 W for the Intel card. This makes it a lower-power option for basic systems or HTPCs where heat and electricity draw are primary concerns. Its PCIe 3.0 x16 interface, while older, is compatible with a wider range of older motherboards, and its DVI output is useful for legacy monitors. For users running older DirectX 9 or 10 titles, the GTX 1060's driver maturity might be a factor, though the fact pack does not provide comparative data for those older APIs. The GTX 1060 is also the physically shorter card at 250 mm versus 272 mm, which could matter in compact cases. Ultimately, the GTX 1060 wins only where power efficiency and legacy I/O are prioritized over performance; everywhere else, the Arc B580's benchmark data makes it the definitive choice.