Intel Arc Pro B60 vs NVIDIA B300 SXM6 AC Comparison

The Verdict

The Intel Arc Pro B60 and NVIDIA B300 SXM6 AC occupy entirely different segments of the GPU market. The data shows the B300 SXM6 AC is a server-class compute accelerator with a 100th percentile ranking among all GPUs, while the Arc Pro B60 sits at the 20th percentile. The B300 SXM6 AC delivers an average benchmark score of 369,831, which is 116 times higher than the Arc Pro B60's average of 3,182. The Arc Pro B60 is suited for professional graphics workstations with display outputs and DirectX 12 Ultimate support, while the B300 SXM6 AC is designed for compute-heavy server workloads with no display outputs and no graphics API support.

Architecture Differences

The Intel Arc Pro B60 uses the BMG-G21 chip based on the Xe2-HPG architecture, part of the Battlemage Pro Series generation. It is built on a 5 nm process at TSMC with 19,600 million transistors on a 272 mm² die, yielding a transistor density of 72.1M per mm². The GPU features 2,560 shading units, 160 texture mapping units, 80 raster operation units, and 20 ray tracing cores. It has no tensor cores. The memory subsystem consists of 24 GB of GDDR6 on a 192-bit bus, delivering 456.0 GB/s of bandwidth. The base clock is 2000 MHz with a boost clock of 2400 MHz, and memory runs at 2375 MHz (19 Gbps effective).

The NVIDIA B300 SXM6 AC uses the GB110 chip based on the Blackwell Ultra architecture, part of the Server Blackwell (Bxx) generation. It is also built on a 5 nm process at TSMC but packs 208,000 million transistors on a much larger 1628 mm² die, achieving a transistor density of 127.8M per mm². This GPU has 18,944 shading units, 592 texture mapping units, 24 raster operation units, and 592 tensor cores. It has no dedicated ray tracing cores. Memory is 288 GB of HBM3e on an 8192-bit bus, providing 8.19 TB/s of bandwidth. The base clock is 1665 MHz with a boost of 2032 MHz, and memory runs at 2000 MHz (8 Gbps effective).

The B300 SXM6 AC uses a 1:1 ratio for FP16 to FP32, delivering 76.99 TFLOPS for both precision levels. The Arc Pro B60 delivers 12.29 TFLOPS FP32 and 24.58 TFLOPS FP16 with a 2:1 ratio. The B300 SXM6 AC has a texture rate of 1,202.9 GTexel/s versus 384.0 GTexel/s for the Arc Pro B60. The Arc Pro B60 has a higher pixel rate at 192.0 GPixel/s compared to 48.77 GPixel/s for the B300 SXM6 AC, reflecting the workstation card's focus on graphics output.

FAQ

Q: Which GPU has higher compute performance?

A: The NVIDIA B300 SXM6 AC delivers 76.99 TFLOPS FP32 and 76.99 TFLOPS FP16, while the Intel Arc Pro B60 provides 12.29 TFLOPS FP32 and 24.58 TFLOPS FP16. The B300 SXM6 AC is 6.3 times faster in FP32 and 3.1 times faster in FP16.

Q: What memory configurations do these GPUs use?

A: The Intel Arc Pro B60 has 24 GB of GDDR6 on a 192-bit bus with 456.0 GB/s bandwidth. The NVIDIA B300 SXM6 AC has 288 GB of HBM3e on an 8192-bit bus with 8.19 TB/s bandwidth, which is 18 times the capacity and 18 times the bandwidth.

Q: Do these GPUs support the same graphics APIs?

A: No. The Intel Arc Pro B60 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The NVIDIA B300 SXM6 AC has no graphics API support, listing DirectX, OpenGL, and Vulkan as N/A.

Q: What are the power requirements?

A: The Intel Arc Pro B60 has a 200 W TDP with a suggested PSU of 550 W and uses a single 8-pin power connector. The NVIDIA B300 SXM6 AC has a 1100 W TDP with a suggested PSU of 1500 W and is an SXM module with no specified power connectors.

Q: Which GPU has display outputs?

A: The Intel Arc Pro B60 has 4x mini-DisplayPort 2.1 outputs. The NVIDIA B300 SXM6 AC has no display outputs, confirming its server-only role.

Q: How do their release dates compare?

A: The Intel Arc Pro B60 was released on September 4, 2025, and the NVIDIA B300 SXM6 AC was released on September 10, 2025, six days later.

Specification Differences

The two GPUs differ in nearly every specification category. The Intel Arc Pro B60 uses the Xe2-HPG architecture with a 5 nm process and 19,600 million transistors on a 272 mm² die. The NVIDIA B300 SXM6 AC uses the Blackwell Ultra architecture, also on 5 nm, but with 208,000 million transistors on a 1628 mm² die. The B300 SXM6 AC has a transistor density of 127.8M per mm² versus 72.1M per mm² for the Arc Pro B60.

Clock speeds differ: the Arc Pro B60 has a base clock of 2000 MHz and boost of 2400 MHz, while the B300 SXM6 AC has a lower base of 1665 MHz and boost of 2032 MHz. Memory differs dramatically: 24 GB GDDR6 at 456.0 GB/s versus 288 GB HBM3e at 8.19 TB/s. The B300 SXM6 AC has a 8192-bit memory bus versus 192-bit for the Arc Pro B60.

Shading units are 2,560 for the Arc Pro B60 versus 18,944 for the B300 SXM6 AC. TMUs are 160 versus 592. ROPs are 80 versus 24. The B300 SXM6 AC has 592 tensor cores, while the Arc Pro B60 has none. The Arc Pro B60 has 20 ray tracing cores, while the B300 SXM6 AC has none.

Pixel rate favors the Arc Pro B60 at 192.0 GPixel/s versus 48.77 GPixel/s. Texture rate favors the B300 SXM6 AC at 1,202.9 GTexel/s versus 384.0 GTexel/s. The Arc Pro B60 uses a PCIe 5.0 x8 interface, while the B300 SXM6 AC uses PCIe 6.0 x16. The Arc Pro B60 has display outputs and graphics API support; the B300 SXM6 AC has neither. Power draw is 200 W versus 1100 W. The Arc Pro B60 is dual-slot with dimensions of 167 mm length, 69 mm height, and 40 mm width. The B300 SXM6 AC is an SXM module with no listed dimensions.

Head-to-Head Benchmarks

The database shows no direct head-to-head benchmark results between these two GPUs. However, the average benchmark scores and percentile rankings provide clear separation. The Intel Arc Pro B60 has an average benchmark score of 3,182, placing it at the 20th percentile among all GPUs. Its nearest rivals include the NVIDIA Quadro P1000 with an average score of 3,163 (0.6% higher), the NVIDIA GeForce GT 640 at 3,210 (0.9% higher), the NVIDIA GeForce 920M at 3,287 (3.2% higher), and the NVIDIA GeForce RTX 5080 SUPER at 3,075 (3.5% lower).

The NVIDIA B300 SXM6 AC has an average benchmark score of 369,831, placing it at the 100th percentile. Its nearest rivals are the NVIDIA B200 at 345,482 (7% lower), the NVIDIA H200 NVL at 334,891 (10.4% lower), the AMD Instinct MI300X at 317,994 (16.3% lower), and the NVIDIA L40S at 295,763 (25% lower). The B300 SXM6 AC leads its closest competitor, the B200, by 7% in average score, and leads the L40S by 25%.

In its own benchmark suite, the Intel Arc Pro B60 scores 14,580 in PassMark G3D, 7,029 in PassMark GPU Compute, 763 in PassMark G2D, and 2,646 in 3DMark Steel Nomad DX12. Its DirectX-specific PassMark scores are 179 for DirectX 9, 122 for DirectX 11, 76 for DirectX 12, and 61 for DirectX 10. The B300 SXM6 AC has a single recorded benchmark: Geekbench OpenCL with a score of 369,831.

The performance gap is substantial. The B300 SXM6 AC's average score of 369,831 is 116.2 times the Arc Pro B60's average of 3,182. The B300 SXM6 AC's FP32 compute of 76.99 TFLOPS is 6.3 times the Arc Pro B60's 12.29 TFLOPS. Memory bandwidth of 8.19 TB/s versus 456.0 GB/s is an 18-fold difference.

Where Each One Wins

The Intel Arc Pro B60 wins in graphics-oriented workloads. It supports DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4, making it suitable for professional 3D applications and content creation. Its pixel rate of 192.0 GPixel/s is 3.9 times higher than the B300 SXM6 AC's 48.77 GPixel/s, indicating stronger rasterization throughput. The Arc Pro B60 has 80 ROPs versus 24, which supports higher fill rates for display output. It provides 4x mini-DisplayPort 2.1 outputs, enabling multi-monitor configurations. The Arc Pro B60 is a dual-slot card with a 200 W TDP and a suggested PSU of 550 W, fitting into workstation builds with standard PCIe 5.0 x8 slots. Its launch MSRP is 499 USD.

The NVIDIA B300 SXM6 AC wins in compute-heavy server workloads. Its FP32 and FP16 performance of 76.99 TFLOPS each dwarfs the Arc Pro B60's figures. The 592 tensor cores accelerate AI and deep learning operations, a capability the Arc Pro B60 lacks entirely. The 288 GB HBM3e memory with 8.19 TB/s bandwidth supports large model training and inference tasks. The B300 SXM6 AC's texture rate of 1,202.9 GTexel/s is 3.1 times the Arc Pro B60's 384.0 GTexel/s. Its average benchmark score of 369,831 places it at the 100th percentile, while the Arc Pro B60 sits at the 20th percentile. The B300 SXM6 AC uses PCIe 6.0 x16, doubling the interface bandwidth of the Arc Pro B60's PCIe 5.0 x8. Its predecessor is Server Hopper, and its successor is Server Rubin, indicating an active server product line.

The B300 SXM6 AC also wins on transistor count and density. It has 208,000 million transistors versus 19,600 million, and a density of 127.8M per mm² versus 72.1M per mm². The B300 SXM6 AC's memory capacity of 288 GB is 12 times the Arc Pro B60's 24 GB. Its 18,944 shading units are 7.4 times the Arc Pro B60's 2,560. The B300 SXM6 AC leads its nearest rivals by significant margins: 7% over the B200, 10.4% over the H200 NVL, 16.3% over the MI300X, and 25% over the L40S.

The Arc Pro B60 wins where graphics output and workstation integration matter. Its display outputs, graphics API support, and higher pixel rate make it the appropriate choice for visual computing tasks. The B300 SXM6 AC wins where raw compute, memory capacity, and AI acceleration dominate. Its lack of display outputs and graphics APIs confirms it is not intended for visual workloads. The data supports a clear separation: the Arc Pro B60 serves graphics professionals, while the B300 SXM6 AC serves data center compute.