Intel Arc Pro A60M vs NVIDIA B300 SXM6 AC Comparison

Head-to-Head Benchmarks

The benchmark data for these two GPUs is extremely lopsided, but the comparison itself reveals how differently the two products are positioned. The Intel Arc Pro A60M has no recorded benchmark entries in the database, while the NVIDIA B300 SXM6 AC has a single entry in Geekbench OpenCL, scoring 369,831 points. That score places the B300 at the 100th percentile of all GPUs in the database, a perfect top-of-stack result.

Against its nearest rivals, the B300 SXM6 AC shows a clear margin of superiority. It outperforms the NVIDIA B200 by 7 percent, the NVIDIA H200 NVL by 10.4 percent, the AMD Instinct MI300X by 16.3 percent, and the NVIDIA L40S by 25 percent. These deltas are recorded across the average benchmark scores of each rival, not just raw clock or memory comparisons, so they represent real measured performance gaps in OpenCL workloads.

The Intel Arc Pro A60M, by contrast, has zero benchmark scores in the database. Its percentile rank of 50 places it exactly in the middle of all GPUs, but there is no measured data to confirm what that rank means in practice. The absence of recorded benchmarks means the head-to-head comparison is effectively a one-sided affair: the NVIDIA part has a verified score, the Intel part does not.

That said, the raw specifications point to a massive gulf in compute capability. The B300 SXM6 AC delivers 76.99 TFLOPS of FP32 performance, while the A60M delivers 5.325 TFLOPS. That is a 13.5x difference in raw single-precision throughput, and the B300 also matches that figure in FP16 with a 1:1 ratio, reaching 76.99 TFLOPS. The A60M's FP16 performance is 10.65 TFLOPS, achieved through a 2:1 ratio, meaning it halves its throughput when moving to half precision.

Texture and pixel rates further illustrate the gap. The B300 reaches 1,202.9 GTexel/s and 48.77 GPixel/s, whereas the A60M manages 166.4 GTexel/s and 83.20 GPixel/s. Interestingly, the Intel part has a higher pixel rate than the NVIDIA part, which is a consequence of the B300's unusually low ROP count of 24 versus the A60M's 64 ROPs. This is a rare instance where the smaller, mobile-oriented GPU wins a raw specification comparison.

Architecture Differences

The two GPUs come from entirely different architectural lineages. The Intel Arc Pro A60M uses the DG2-256 chip built on the Xe-HPG architecture, part of the Alchemist generation for professional mobile systems. It is fabricated on a 6 nm process at TSMC, with 11,500 million transistors packed into a 269 mm² die, yielding a transistor density of 42.8 million per square millimeter.

The NVIDIA B300 SXM6 AC uses the GB110 chip based on the Blackwell Ultra architecture, belonging to the Server Blackwell generation. It is also made by TSMC, but on a 5 nm process, and it scales dramatically: 208,000 million transistors on a 1628 mm² die, giving a density of 127.8 million per square millimeter. That is roughly 18 times the transistor count and 6 times the die area of the Intel part.

Memory configurations could hardly be more different. The A60M uses 8 GB of GDDR6 on a 128-bit bus, achieving 256.0 GB/s of bandwidth. The B300 uses 288 GB of HBM3e on an 8192-bit bus, achieving 8.19 TB/s, which is 32 times the bandwidth of the Intel part. The NVIDIA GPU also has a much larger memory pool, 36 times the capacity.

The compute units also differ in structure. The A60M has 2048 shading units, 128 texture mapping units, 64 ROPs, and 16 ray tracing cores. The B300 has 18,944 shading units, 592 TMUs, and 24 ROPs, plus 592 tensor cores. The Intel part does not list tensor cores, while the NVIDIA part does not list dedicated RT cores, reflecting their different focus areas: the A60M is oriented toward professional graphics workloads with ray tracing support, while the B300 is a compute-first server accelerator with tensor core emphasis.

Clock speeds also differ substantially. The Intel GPU runs at a 900 MHz base and 1300 MHz boost, while the NVIDIA GPU runs at 1665 MHz base and 2032 MHz boost. The memory clocks are similar in name, both listed at 2000 MHz, but the effective data rates diverge: the A60M reaches 16 Gbps effective, while the B300 reaches only 8 Gbps effective, though the latter's massive bus width more than compensates.

Power and form factor represent another chasm. The A60M has a 95 W TDP and an IGP slot width, meaning it is designed to be integrated into a portable device. The B300 has a 1100 W TDP, an SXM module slot width, and a suggested PSU of 1500 W. The bus interfaces also differ: the A60M uses PCIe 4.0 x16, while the B300 uses PCIe 6.0 x16. Display outputs are portable-device-dependent for Intel and absent entirely for NVIDIA.

Where Each One Wins

The Intel Arc Pro A60M wins in specific niche areas that favor its design goals. Its pixel rate of 83.20 GPixel/s exceeds the B300's 48.77 GPixel/s, which is notable given the B300's far larger compute resources. This is likely due to the A60M's higher ROP count of 64 versus 24, making it more efficient at fill-rate-bound tasks such as traditional rasterization. The A60M also supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, while the B300 lists N/A for all three APIs, meaning the Intel part is the only one of the two that can run conventional graphics workloads with those APIs.

The A60M also wins on power efficiency. At 95 W TDP, it consumes roughly 8.6 percent of the B300's 1100 W TDP. For mobile or low-power professional environments, this makes it a far more practical option, though the database does not contain measured performance-per-watt figures to quantify the tradeoff precisely. Its smaller die size of 269 mm² versus 1628 mm² also makes it cheaper to produce in theory, though pricing data is not available.

The NVIDIA B300 SXM6 AC wins in every compute-heavy category. Its FP32 throughput of 76.99 TFLOPS is 14.5 times higher than the A60M's 5.325 TFLOPS. Its FP16 throughput is 7.2 times higher at 76.99 TFLOPS versus 10.65 TFLOPS, and it achieves that at a 1:1 ratio rather than a 2:1 ratio, meaning no performance penalty for half-precision work. Its texture rate of 1,202.9 GTexel/s is 7.2 times higher than the A60M's 166.4 GTexel/s.

Memory bandwidth is where the B300 is most dominant. Its 8.19 TB/s bandwidth is 32 times the A60M's 256.0 GB/s, and its 288 GB capacity is 36 times larger. For workloads that are memory-bound, such as large language model inference or scientific simulation, this advantage is decisive. The B300 also has a 100th percentile rank among all GPUs, while the A60M sits at the 50th percentile.

The B300's only recorded benchmark, Geekbench OpenCL at 369,831, confirms its position at the top of the database. Its nearest rival, the NVIDIA B200, scores 345,482, which is 7 percent lower. The H200 NVL at 334,891 is 10.4 percent lower, and the MI300X at 317,994 is 16.3 percent lower. The L40S at 295,763 trails by 25 percent.

FAQ

Q: Which GPU has higher FP32 performance?

A: The NVIDIA B300 SXM6 AC delivers 76.99 TFLOPS of FP32, compared to the Intel Arc Pro A60M's 5.325 TFLOPS.

Q: How much memory bandwidth does each GPU provide?

A: The B300 SXM6 AC offers 8.19 TB/s from 288 GB of HBM3e on an 8192-bit bus. The A60M offers 256.0 GB/s from 8 GB of GDDR6 on a 128-bit bus.

Q: Which GPU supports DirectX 12 Ultimate?

A: Only the Intel Arc Pro A60M lists DirectX 12 Ultimate (12_2) support, along with OpenGL 4.6 and Vulkan 1.4. The NVIDIA B300 SXM6 AC lists N/A for all three APIs.

Q: What is the transistor count difference between the two?

A: The B300 SXM6 AC has 208,000 million transistors on a 1628 mm² die, while the A60M has 11,500 million transistors on a 269 mm² die.

Q: How does the B300 compare to its closest rival in the database?

A: The B300 scores 369,831 in Geekbench OpenCL, which is 7 percent higher than the NVIDIA B200 at 345,482 and 10.4 percent higher than the NVIDIA H200 NVL at 334,891.

Q: What are the power requirements for each GPU?

A: The A60M has a 95 W TDP and uses an IGP slot width. The B300 has a 1100 W TDP, uses an SXM module slot width, and requires a suggested PSU of 1500 W.

Specification Differences

| Specification | Intel Arc Pro A60M | NVIDIA B300 SXM6 AC |

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

| Chip | DG2-256 | GB110 |

| Architecture | Xe-HPG | Blackwell Ultra |

| Generation | Alchemist (Pro-Series Mobile) | Server Blackwell (Bxx) |

| Process Node | 6 nm | 5 nm |

| Transistors | 11,500 million | 208,000 million |

| Die Size | 269 mm² | 1628 mm² |

| Transistor Density | 42.8M / mm² | 127.8M / mm² |

| Base Clock | 900 MHz | 1665 MHz |

| Boost Clock | 1300 MHz | 2032 MHz |

| Memory Clock | 2000 MHz, 16 Gbps effective | 2000 MHz, 8 Gbps effective |

| Memory Size | 8 GB | 288 GB |

| Memory Type | GDDR6 | HBM3e |

| Memory Bus Width | 128 bit | 8192 bit |

| Memory Bandwidth | 256.0 GB/s | 8.19 TB/s |

| Shading Units | 2048 | 18944 |

| TMUs | 128 | 592 |

| ROPs | 64 | 24 |

| RT Cores | 16 | N/A |

| Tensor Cores | N/A | 592 |

| Pixel Rate | 83.20 GPixel/s | 48.77 GPixel/s |

| Texture Rate | 166.4 GTexel/s | 1,202.9 GTexel/s |

| FP32 Performance | 5.325 TFLOPS | 76.99 TFLOPS |

| FP16 Performance | 10.65 TFLOPS (2:1) | 76.99 TFLOPS (1:1) |

| TDP | 95 W | 1100 W |

| Slot Width | IGP | SXM Module |

| Suggested PSU | N/A | 1500 W |

| Bus Interface | PCIe 4.0 x16 | PCIe 6.0 x16 |

| Display Outputs | Portable Device Dependent | No outputs |

| DirectX Support | 12 Ultimate (12_2) | N/A |

| OpenGL Support | 4.6 | N/A |

| Vulkan Support | 1.4 | N/A |

| Release Date | 2023-06-05 | 2025-09-10 |

| Predecessor | N/A | Server Hopper |

| Successor | N/A | Server Rubin |

| Percentile vs All GPUs | 50 | 100 |

| Average Benchmark Score | 0 | 369831 |