Intel Arc B580 vs Intel Arc Pro B60 Dual Comparison

FAQ

Q: What are the core hardware specifications of the Intel Arc B580?

A: The Intel Arc B580 uses the BMG-G21 chip on the Xe2-HPG architecture, built on a 5 nm process at TSMC. It has 19,600 million transistors on a 272 mm² die, with 2560 shading units, 160 TMUs, 80 ROPs, and 20 RT cores. The GPU runs at a base and boost clock of 2670 MHz.

Q: How does the memory configuration differ between the two cards?

A: The Arc B580 has 12 GB of GDDR6 memory on a 192-bit bus with 456.0 GB/s bandwidth. The Arc Pro B60 Dual has 24 GB of GDDR6 memory, also on a 192-bit bus with the same 456.0 GB/s bandwidth. Both use 2375 MHz memory with 19 Gbps effective speed.

Q: What are the compute performance differences in raw numbers?

A: The Arc B580 delivers 13.67 TFLOPS FP32 and 27.34 TFLOPS FP16 (2:1). The Arc Pro B60 Dual delivers 12.29 TFLOPS FP32 and 24.58 TFLOPS FP16 (2:1). The pixel rate is 213.6 GPixel/s for the B580 versus 192.0 GPixel/s for the Pro B60, and texture rates are 427.2 GTexel/s versus 384.0 GTexel/s.

Q: Do both cards use the same underlying architecture?

A: Yes, both use the Xe2-HPG architecture with the BMG-G21 chip, 5 nm TSMC process, 19,600 million transistors, and 272 mm² die size. They share identical counts of shading units, TMUs, ROPs, and RT cores.

Q: What are the power requirements for each card?

A: The Arc B580 has a TDP of 190 W with a suggested PSU of 450 W and uses a 1x 8-pin power connector. The Arc Pro B60 Dual has a TDP of 400 W with a suggested PSU of 800 W and uses a 1x 16-pin power connector.

Q: How do the benchmark scores for the Arc B580 compare to its nearest rivals?

A: The Arc B580 has an average benchmark score of 23021. It sits within 1% of several rivals: 0.2% behind the AMD Radeon RX 580 2048SP (23061), 0.6% ahead of the NVIDIA GeForce RTX 2080 (22895), 0.7% behind the NVIDIA GeForce RTX 3080 (23172), and 1% behind the NVIDIA P106-100 (23249).

Architecture Differences

Both cards share the same foundational architecture. The Intel Arc B580 and Intel Arc Pro B60 Dual are built on the Xe2-HPG architecture using the identical BMG-G21 chip. The die size is exactly the same at 272 mm², and both pack 19,600 million transistors on a 5 nm TSMC process. The transistor density works out to 72.1M per mm² for both.

The compute core layout is identical: 2560 shading units, 160 texture mapping units, 80 raster output units, and 20 ray tracing cores. Neither card has distinct tensor cores listed. The API support matches completely, with DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4 on both.

The differentiation comes from clock speeds and power allocation. The Arc B580 runs at a flat 2670 MHz for both base and boost clocks. The Arc Pro B60 Dual runs at a 2000 MHz base clock and 2400 MHz boost clock. This clock reduction directly explains the lower fill rates and compute throughput on the Pro model.

Memory architecture is shared in bus width and bandwidth. Both use a 192-bit GDDR6 interface delivering 456.0 GB/s at 2375 MHz (19 Gbps effective). The difference is capacity: 12 GB on the B580 versus 24 GB on the Pro B60 Dual.

The power delivery and board design diverge significantly. The Arc B580 draws up to 190 W, uses a single 8-pin connector, and recommends a 450 W PSU. The Arc Pro B60 Dual draws up to 400 W, requires a single 16-pin connector, and recommends an 800 W PSU. The Pro card is longer at 300 mm versus 272 mm, but slightly narrower and thinner.

The PCIe interface also differs. The Arc B580 uses PCIe 4.0 x8, while the Arc Pro B60 Dual uses PCIe 5.0 x8. Display outputs are another split: the B580 has 1x HDMI 2.1a and 3x DisplayPort 2.1, while the Pro B60 Dual has 4x mini-DisplayPort 2.1.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark comparisons between these two cards. The Arc B580 has a full benchmark suite recorded, while the Arc Pro B60 Dual has no benchmark entries in the database. This absence of data means direct performance comparisons must be inferred from the specification differences.

The recorded benchmarks for the Arc B580 show its standing in the broader GPU landscape. In 3DMark Steel Nomad DX12, it scores 3068. Geekbench results show 92821 in OpenCL and 109672 in Vulkan. Passmark scores include 76 in DirectX 10, 128 in DirectX 11, 76 in DirectX 12, 183 in DirectX 9, 709 in G2D, 15748 in G3D, and 7729 in GPU Compute.

The Arc B580 holds the 68th percentile among all GPUs in the database. Its nearest rivals include the AMD Radeon RX 580 2048SP at 23061 average score (0.2% ahead), the NVIDIA GeForce RTX 2080 at 22895 (0.6% behind), the NVIDIA GeForce RTX 3080 at 23172 (0.7% ahead), and the NVIDIA P106-100 at 23249 (1% ahead).

Without any recorded benchmarks for the Arc Pro B60 Dual, the performance relationship must be derived from compute specifications. The Arc B580's 13.67 TFLOPS FP32 represents a 10% advantage over the Pro B60 Dual's 12.29 TFLOPS. The pixel rate advantage is similar: 213.6 GPixel/s versus 192.0 GPixel/s, a difference of about 10%. Texture rate follows the same pattern at 427.2 GTexel/s versus 384.0 GTexel/s.

The clock speed gap explains these differences. The B580's 2670 MHz boost exceeds the Pro B60's 2400 MHz boost by 11%. The Pro card's 400 W TDP does not translate into higher performance; instead, it likely reflects different board power delivery for sustained professional workloads rather than raw speed.

The Verdict

The data indicates two cards with identical core architectures but different purposes. The Arc B580 is positioned for general graphics workloads, evidenced by its higher clock speeds, higher compute throughput, and its placement at the 68th percentile among all GPUs. Its benchmark scores place it in the same performance band as the NVIDIA RTX 2080 and RTX 3080, with deltas under 1%.

The Arc Pro B60 Dual targets a different segment. Its 24 GB memory capacity doubles the B580's 12 GB, which matters for large datasets and high-resolution textures. However, its lower clocks reduce raw compute: 12.29 TFLOPS FP32 versus 13.67 TFLOPS, and a 192.0 GPixel/s pixel rate versus 213.6 GPixel/s.

The 400 W TDP and 800 W suggested PSU indicate the Pro card is built for sustained, heavy workloads rather than peak clock speeds. The PCIe 5.0 x8 interface provides double the bandwidth of the B580's PCIe 4.0 x8 connection. The mini-DisplayPort 2.1 outputs (4x) suggest professional display configurations.

Users who prioritize raw frame throughput and clock speed should favor the Arc B580. Users who need large memory capacity, professional display outputs, and PCIe 5.0 connectivity should consider the Arc Pro B60 Dual, accepting lower compute rates. The Arc B580's recorded benchmark performance at the 68th percentile gives it a clear measured advantage in general graphics; the Pro B60's advantages are in capacity and interface features, not speed.

Specification Differences

| Specification | Intel Arc B580 | Intel Arc Pro B60 Dual |

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

| Generation | Battlemage (Arc 5) | Battlemage (Pro Series) |

| Base Clock | 2670 MHz | 2000 MHz |

| Boost Clock | 2670 MHz | 2400 MHz |

| Memory Size | 12 GB | 24 GB |

| Pixel Rate | 213.6 GPixel/s | 192.0 GPixel/s |

| Texture Rate | 427.2 GTexel/s | 384.0 GTexel/s |

| FP32 | 13.67 TFLOPS | 12.29 TFLOPS |

| FP16 | 27.34 TFLOPS (2:1) | 24.58 TFLOPS (2:1) |

| TDP | 190 W | 400 W |

| Power Connectors | 1x 8-pin | 1x 16-pin |

| Suggested PSU | 450 W | 800 W |

| Bus Interface | PCIe 4.0 x8 | PCIe 5.0 x8 |

| Display Outputs | 1x HDMI 2.1a, 3x DisplayPort 2.1 | 4x mini-DisplayPort 2.1 |

| Length | 272 mm (10.7 inches) | 300 mm (11.8 inches) |

| Height | 115 mm (4.5 inches) | 110 mm (4.3 inches) |

| Width | 45 mm (1.8 inches) | 40 mm (1.6 inches) |

| Release Date | 2024-12-12 | 2025-09-04 |

| Launch MSRP | 249 USD | 1,199 USD |

| Percentile | 68 | 50 |

| Average Benchmark Score | 23021 | 0 |

Where Each One Wins

The Arc B580 wins decisively in raw compute performance. Its 13.67 TFLOPS FP32 output is measurably higher than the Pro B60's 12.29 TFLOPS. The pixel rate advantage of 213.6 GPixel/s versus 192.0 GPixel/s means faster rasterization throughput. Texture rate follows at 427.2 GTexel/s versus 384.0 GTexel/s. The higher boost clock of 2670 MHz versus 2400 MHz drives all of these wins.

The Arc B580 also wins on power efficiency in the data. It achieves higher performance at 190 W TDP, while the Pro B60 Dual consumes 400 W for lower throughput. The B580's suggested PSU of 450 W versus 800 W reflects a lighter system power burden. The B580 is also shorter at 272 mm versus 300 mm, which improves case compatibility.

The Arc B580 wins on verified benchmark standing. Its average score of 23021 and 68th percentile placement come from actual recorded tests. The Pro B60 Dual has no recorded benchmarks, placing it at the 50th percentile by default with an average score of zero.

The Arc Pro B60 Dual wins on memory capacity. Its 24 GB doubles the B580's 12 GB, providing substantially more headroom for large working sets. This capacity advantage is the primary differentiator in the data. The memory bandwidth remains identical at 456.0 GB/s, so the extra capacity does not come with faster transfers.

The Pro B60 Dual wins on interface modernity. Its PCIe 5.0 x8 bus doubles the bandwidth of the B580's PCIe 4.0 x8 connection. This matters for data-intensive workloads that move large buffers between system memory and GPU memory. The Pro card also offers four mini-DisplayPort 2.1 outputs, while the B580 offers one HDMI 2.1a and three DisplayPort 2.1.

The Pro B60 Dual's 400 W TDP and 16-pin connector suggest a board designed for sustained professional operation, though the recorded data does not include benchmarks that would confirm this behavior. The 800 W suggested PSU indicates a higher system power requirement.

The use-case split is clear from the data: the Arc B580 serves general graphics with higher clock speeds and verified benchmark performance, while the Arc Pro B60 Dual serves capacity-hungry professional workflows with double the memory and a faster system bus.