Intel Arc Pro B60 Dual vs NVIDIA B300 SXM6 AC Comparison

Head-to-Head Benchmarks

The recorded data shows no direct head-to-head benchmark results between the Intel Arc Pro B60 Dual and the NVIDIA B300 SXM6 AC. The Intel Arc Pro B60 Dual has no benchmark entries in the database, while the NVIDIA B300 SXM6 AC holds a single Geekbench OpenCL score of 369,831. This absence of overlapping test data means a direct performance comparison cannot be established from the measurements available.

The NVIDIA B300 SXM6 AC achieves a perfect percentile ranking of 100 among all GPUs in the database, indicating it outperforms every other recorded GPU. Its average benchmark score of 369,831 places it ahead of its nearest rivals. The NVIDIA B200 scores 345,482, which is 7 percent lower. The NVIDIA H200 NVL records 334,891, trailing by 10.4 percent. The AMD Instinct MI300X reaches 317,994, a deficit of 16.3 percent. The NVIDIA L40S posts 295,763, sitting 25 percent behind the B300 SXM6 AC.

The Intel Arc Pro B60 Dual has no benchmark scores, no nearest rivals, and a percentile rank of 50, which places it at the median of all recorded GPUs. Without a benchmark value, the data cannot quantify its standing against the B300 SXM6 AC or any other accelerator. The percentile of 50 suggests it is neither a top performer nor a bottom-tier device, but the lack of an average score prevents any numerical comparison.

The B300 SXM6 AC demonstrates a clear hierarchy among its competitors. The 7 percent gap over the B200 shows a modest generational improvement within the same family. The 10.4 percent lead over the H200 NVL indicates the B300 SXM6 AC extends beyond the previous Hopper-generation flagship. The 16.3 percent advantage over the AMD Instinct MI300X shows a substantial margin over the leading AMD server accelerator. The 25 percent lead over the NVIDIA L40S illustrates a wide performance gulf, though the L40S targets a different market segment.

For the Intel Arc Pro B60 Dual, the data provides no basis for a head-to-head narrative. The database records zero wins for either side in direct comparisons. All performance interpretation for the Intel card must rely on its architectural specifications rather than measured results.

Architecture Differences

The Intel Arc Pro B60 Dual uses the BMG-G21 chip built on the Xe2-HPG architecture, part of the Battlemage Pro Series generation. The NVIDIA B300 SXM6 AC uses the GB110 chip built on the Blackwell Ultra architecture, part of the Server Blackwell Bxx generation. Both use a 5 nm process node from TSMC, but the transistor counts differ dramatically. The Intel chip contains 19,600 million transistors on a 272 mm² die, yielding a transistor density of 72.1 million per mm². The NVIDIA chip packs 208,000 million transistors on a 1,628 mm² die, achieving 127.8 million per mm². The NVIDIA die is roughly six times larger in area and holds over ten times more transistors.

Clock behavior differs between the two. The Intel GPU runs at a base clock of 2000 MHz and boosts to 2400 MHz. The NVIDIA GPU operates at a lower base of 1665 MHz and boosts to 2032 MHz. Despite lower clocks, the NVIDIA chip delivers far higher compute throughput due to its massive shader count. The Intel card has 2,560 shading units, while the NVIDIA card has 18,944, a ratio of roughly 7.4 to 1. Texture mapping units number 160 on Intel versus 592 on NVIDIA. Raster operation units tell a different story: Intel has 80 ROPs, NVIDIA has only 24. The Intel card also includes 20 ray tracing cores, while the NVIDIA card lists no dedicated RT core count. The NVIDIA card includes 592 tensor cores, a feature the Intel card does not specify.

Memory architecture shows stark contrasts. The Intel Arc Pro B60 Dual uses 24 GB of GDDR6 on a 192-bit bus, producing 456.0 GB/s of bandwidth. The NVIDIA B300 SXM6 AC uses 288 GB of HBM3e on an 8192-bit bus, delivering 8.19 TB/s, which is nearly 18 times the bandwidth of the Intel card. Memory clocks differ as well: Intel runs at 2375 MHz with 19 Gbps effective, while NVIDIA runs at 2000 MHz with 8 Gbps effective. The NVIDIA memory clock is lower, but the enormous bus width compensates to create a massive bandwidth advantage.

Compute rates reflect the architectural gulf. The Intel card reaches 12.29 TFLOPS for FP32 and 24.58 TFLOPS for FP16 with a 2:1 ratio. The NVIDIA card delivers 76.99 TFLOPS for both FP32 and FP16 with a 1:1 ratio. NVIDIA's FP32 figure is 6.27 times higher than Intel's. Pixel rates favor Intel: 192.0 GPixel/s versus 48.77 GPixel/s, driven by the higher ROP count. Texture rates favor NVIDIA massively: 1,202.9 GTexel/s versus 384.0 GTexel/s.

Power and interface specifications diverge completely. The Intel card has a TDP of 400 W and requires a suggested power supply of 800 W, using a single 16-pin connector. The NVIDIA card has a TDP of 1100 W and a suggested power supply of 1500 W, with no listed power connectors as it is an SXM module. The Intel card uses PCIe 5.0 x8, while the NVIDIA card uses PCIe 6.0 x16. The Intel card is a dual-slot design measuring 300 mm in length, 110 mm in height, and 40 mm in width. The NVIDIA card is an SXM module with no listed dimensions. The Intel card provides 4x mini-DisplayPort 2.1 outputs and supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The NVIDIA card has no display outputs and lists no API support in the database.

Where Each One Wins

The NVIDIA B300 SXM6 AC wins decisively in raw compute workloads. Its FP32 throughput of 76.99 TFLOPS dwarfs the Intel card's 12.29 TFLOPS. For FP16 workloads, the NVIDIA card again leads with 76.99 TFLOPS versus 24.58 TFLOPS, though the Intel card's 2:1 ratio shows it can accelerate FP16 relative to its own FP32. The NVIDIA card's 288 GB of HBM3e memory with 8.19 TB/s bandwidth suits large model inference and training datasets, while the Intel card's 24 GB GDDR6 with 456.0 GB/s targets lighter workloads.

Texture-heavy rendering favors NVIDIA. The B300 SXM6 AC produces 1,202.9 GTexel/s compared to 384.0 GTexel/s on the Intel card. The 592 texture mapping units on NVIDIA vastly outnumber the 160 on Intel. However, rasterization throughput favors Intel. The Arc Pro B60 Dual delivers 192.0 GPixel/s versus 48.77 GPixel/s on the B300 SXM6 AC, and its 80 ROPs outnumber NVIDIA's 24. The Intel card also supports display outputs with four mini-DisplayPort 2.1 connections, while the NVIDIA card has none. This makes the Intel card viable for workstation visual output, whereas the NVIDIA card is a compute-only server module.

The Intel card includes 20 ray tracing cores, a feature absent from the NVIDIA card's listed specifications. DirectX 12 Ultimate support on the Intel card enables modern gaming and real-time graphics features, while the NVIDIA card lists no DirectX, OpenGL, or Vulkan support, confirming its server-oriented design. The Intel card's lower TDP of 400 W versus 1100 W means it fits into systems with modest power delivery, though the database does not provide efficiency metrics.

The NVIDIA card wins on memory capacity by a factor of 12, on memory bandwidth by a factor of roughly 18, on shader count by a factor of 7.4, and on FP32 compute by a factor of 6.27. The Intel card wins on pixel fill rate by a factor of 3.94, on ROP count by a factor of 3.33, and on clock speed, with a boost of 2400 MHz versus 2032 MHz. The Intel card also supports display outputs and standard graphics APIs, which the NVIDIA card lacks entirely.

FAQ

Q: What benchmark score does the NVIDIA B300 SXM6 AC achieve?

A: The NVIDIA B300 SXM6 AC records a Geekbench OpenCL score of 369,831, which is its only benchmark entry and gives it a percentile rank of 100 among all GPUs in the database.

Q: How does the NVIDIA B300 SXM6 AC compare to its nearest rivals?

A: The database shows the NVIDIA B200 scores 345,482, which is 7 percent lower. The NVIDIA H200 NVL scores 334,891, 10.4 percent lower. The AMD Instinct MI300X scores 317,994, 16.3 percent lower. The NVIDIA L40S scores 295,763, 25 percent lower.

Q: Does the Intel Arc Pro B60 Dual have any benchmark results?

A: No. The Intel Arc Pro B60 Dual has an empty benchmark list and an average benchmark score of 0. Its percentile rank of 50 places it at the median of all GPUs, but no measured performance data exists.

Q: What are the memory specifications for each card?

A: The Intel card has 24 GB of GDDR6 on a 192-bit bus with 456.0 GB/s bandwidth. The NVIDIA card has 288 GB of HBM3e on an 8192-bit bus with 8.19 TB/s bandwidth.

Q: What is the transistor count difference?

A: The Intel BMG-G21 chip contains 19,600 million transistors on a 272 mm² die. The NVIDIA GB110 chip contains 208,000 million transistors on a 1,628 mm² die.

Q: Do both cards support display outputs?

A: No. The Intel Arc Pro B60 Dual has 4x mini-DisplayPort 2.1 outputs and supports DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4. The NVIDIA B300 SXM6 AC has no display outputs and lists no API support.

Specification Differences

The two cards differ across nearly every specification field. The process node is identical at 5 nm from TSMC, but the chip designs diverge completely. The Intel chip is the BMG-G21 with 19,600 million transistors on a 272 mm² die. The NVIDIA chip is the GB110 with 208,000 million transistors on a 1,628 mm² die. Transistor density reads 72.1M per mm² for Intel and 127.8M per mm² for NVIDIA.

Clock speeds differ: Intel runs at 2000 MHz base and 2400 MHz boost, while NVIDIA runs at 1665 MHz base and 2032 MHz boost. Memory clocks also differ: Intel uses 2375 MHz with 19 Gbps effective, while NVIDIA uses 2000 MHz with 8 Gbps effective. Memory size, type, bus width, and bandwidth all differ: 24 GB GDDR6 on 192-bit with 456.0 GB/s versus 288 GB HBM3e on 8192-bit with 8.19 TB/s.

Shader resources differ: Intel has 2,560 shading units, 160 TMUs, 80 ROPs, and 20 RT cores. NVIDIA has 18,944 shading units, 592 TMUs, 24 ROPs, and 592 tensor cores, with no RT core count listed. Compute rates differ: Intel achieves 192.0 GPixel/s, 384.0 GTexel/s, 12.29 TFLOPS FP32, and 24.58 TFLOPS FP16. NVIDIA achieves 48.77 GPixel/s, 1,202.9 GTexel/s, 76.99 TFLOPS FP32, and 76.99 TFLOPS FP16.

Power specifications differ: Intel has a 400 W TDP with an 800 W suggested PSU and a single 16-pin connector. NVIDIA has an 1100 W TDP with a 1500 W suggested PSU and no listed connectors. The bus interface differs: PCIe 5.0 x8 for Intel versus PCIe 6.0 x16 for NVIDIA. Display outputs differ: 4x mini-DisplayPort 2.1 for Intel versus no outputs for NVIDIA. API support differs: Intel lists DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4, while NVIDIA lists N/A for all. Dimensions differ: Intel measures 300 mm by 110 mm by 40 mm as a dual-slot card, while NVIDIA is an SXM module with no listed dimensions. Release dates differ by six days: Intel on 2025-09-04 and NVIDIA on 2025-09-10. The Intel card has a launch MSRP of 1,199 USD, while the NVIDIA card has no listed launch MSRP. The NVIDIA card lists a predecessor, Server Hopper, and a successor, Server Rubin, while the Intel card lists neither.

The Verdict

The data presents two accelerators built for entirely different purposes. The NVIDIA B300 SXM6 AC dominates the measured benchmark landscape with a Geekbench OpenCL score of 369,831 and a perfect 100 percentile ranking. Its nearest competitor, the NVIDIA B200, sits 7 percent lower, and the gap widens to 25 percent against the NVIDIA L40S. The B300 SXM6 AC delivers 76.99 TFLOPS of FP32 and FP16 compute, 288 GB of HBM3e memory, and 8.19 TB/s of bandwidth. These figures position it as a top-tier server accelerator for compute-heavy workloads, consistent with its Server Blackwell generation and SXM module form factor.

The Intel Arc Pro B60 Dual has no measured benchmark data. Its percentile rank of 50 places it at the median, but without a score, the database cannot confirm its actual performance. Its specifications show a workstation-oriented card: 12.29 TFLOPS FP32, 24 GB GDDR6, 456.0 GB/s bandwidth, 20 ray tracing cores, and four mini-DisplayPort 2.1 outputs. The pixel rate of 192.0 GPixel/s exceeds the NVIDIA card's 48.77 GPixel/s, and the 80 ROPs outnumber NVIDIA's 24. This suggests the Intel card handles rasterization and display output more effectively, while the NVIDIA card focuses exclusively on compute throughput.

The choice between the two depends on the workload. The NVIDIA B300 SXM6 AC suits large-scale compute tasks requiring massive memory capacity, extreme FP32 and FP16 throughput, and tensor core acceleration. The Intel Arc Pro B60 Dual suits workstation graphics tasks requiring display output, modern graphics API support, and ray tracing capability. The NVIDIA card's lack of display outputs and API support confirms it is not intended for interactive graphics. The Intel card's 400 W TDP and dual-slot design make it a conventional add-in card, while the NVIDIA card's 1100 W TDP and SXM form factor require a server chassis with dedicated power delivery.

The recorded data shows no direct comparison, so any head-to-head verdict must rely on specification analysis. The NVIDIA B300 SXM6 AC holds the only benchmark score in the database and ranks at the very top of all GPUs. The Intel Arc Pro B60 Dual holds no benchmark score and ranks at the median. For raw compute performance, the NVIDIA card is the clear choice based on available data. For graphics-oriented workloads with display output, the Intel card offers features the NVIDIA card cannot provide. The database records no wins for either card in direct competition, leaving the final determination to the specific requirements of the use case.