Intel Arc Pro B60 Dual vs NVIDIA GeForce RTX 5090 D Comparison

# FAQ

Q: What are the launch MSRP values for the Intel Arc Pro B60 Dual and the NVIDIA GeForce RTX 5090 D?

A: The Intel Arc Pro B60 Dual has a launch MSRP of 1,199 USD, while the NVIDIA GeForce RTX 5090 D has a launch MSRP of 2,299 USD.

Q: Which GPU has more memory and what type?

A: The NVIDIA GeForce RTX 5090 D carries 32 GB of GDDR7 memory on a 512-bit bus, delivering 1.79 TB/s of bandwidth. The Intel Arc Pro B60 Dual has 24 GB of GDDR6 memory on a 192-bit bus, providing 456.0 GB/s.

Q: How do the transistor counts compare between the two chips?

A: The NVIDIA GB202 chip contains 92,200 million transistors on a 750 mm² die. The Intel BMG-G21 chip has 19,600 million transistors on a 272 mm² die. Both are fabricated on TSMC's 5 nm process node, but the NVIDIA chip achieves a higher transistor density of 122.9M / mm² versus 72.1M / mm² for Intel.

Q: What is the average benchmark score for each GPU?

A: The database records an average benchmark score of 77712 for the NVIDIA GeForce RTX 5090 D. The Intel Arc Pro B60 Dual has no recorded benchmark scores and an average benchmark score of 0.

Q: Which GPU holds a higher percentile ranking among all GPUs?

A: The NVIDIA GeForce RTX 5090 D ranks in the 92nd percentile of all GPUs. The Intel Arc Pro B60 Dual sits at the 50th percentile.

Q: What are the release dates for these cards?

A: The NVIDIA GeForce RTX 5090 D was released on 2025-01-29, and the Intel Arc Pro B60 Dual followed on 2025-09-04.

Architecture Differences

The fundamental architecture split between these two GPUs is substantial. Intel's Arc Pro B60 Dual uses the Xe2-HPG architecture, built around the BMG-G21 chip, and belongs to the Battlemage (Pro Series) generation. NVIDIA's GeForce RTX 5090 D uses the Blackwell 2.0 architecture, built around the GB202 chip, and belongs to the GeForce 50 series.

Both chips are fabricated on TSMC's 5 nm process node, but the scale of the silicon differs dramatically. The GB202 die measures 750 mm² and packs 92,200 million transistors, while the BMG-G21 die measures 272 mm² with 19,600 million transistors. This translates to a transistor density of 122.9M / mm² for NVIDIA versus 72.1M / mm² for Intel, indicating that NVIDIA's design is both larger and denser.

The compute resources reflect this disparity. NVIDIA's GPU fields 21,760 shading units, 680 texture mapping units, 176 raster output units, 170 ray tracing cores, and 680 tensor cores. Intel's GPU offers 2,560 shading units, 160 TMUs, 80 ROPs, and 20 ray tracing cores, with no dedicated tensor core count listed. The FP32 compute throughput is 104.8 TFLOPS for NVIDIA versus 12.29 TFLOPS for Intel. FP16 performance shows a notable difference in ratio: NVIDIA delivers 104.8 TFLOPS at 1:1 ratio, while Intel provides 24.58 TFLOPS at 2:1 ratio.

Memory architecture also diverges. NVIDIA uses 32 GB of GDDR7 on a 512-bit bus, yielding 1.79 TB/s bandwidth. Intel uses 24 GB of GDDR6 on a 192-bit bus, yielding 456.0 GB/s. Clock speeds are similar at the base level (2017 MHz for NVIDIA versus 2000 MHz for Intel) and boost level (2407 MHz versus 2400 MHz), but the memory clocks differ: 1750 MHz (28 Gbps effective) for NVIDIA versus 2375 MHz (19 Gbps effective) for Intel.

The PCIe interface differs as well. NVIDIA connects via PCIe 5.0 x16, while Intel uses PCIe 5.0 x8. Display outputs also diverge: NVIDIA provides 1x HDMI 2.1b and 3x DisplayPort 2.1b, whereas Intel provides 4x mini-DisplayPort 2.1.

Where Each One Wins

The recorded data shows a clear winner in most categories: the NVIDIA GeForce RTX 5090 D. Based on its 92nd percentile ranking and an average benchmark score of 77712, this GPU is positioned for high-end rendering, ray tracing, and compute workloads. Its 104.8 TFLOPS FP32 throughput and 104.8 TFLOPS FP16 throughput indicate strong general compute and AI-oriented performance. The 32 GB GDDR7 memory with 1.79 TB/s bandwidth supports large datasets and high-resolution textures.

The Intel Arc Pro B60 Dual, with its 50th percentile ranking and no recorded benchmark scores, targets a different segment. Its 24 GB GDDR6 memory and 456.0 GB/s bandwidth are modest, but the card's 12.29 TFLOPS FP32 and 24.58 TFLOPS FP16 (2:1) still offer usable compute capability. The 20 ray tracing cores and Xe2-HPG architecture provide hardware-accelerated ray tracing, though the raw throughput is far lower than NVIDIA's 170 RT cores.

In terms of power requirements, NVIDIA demands a 575 W TDP and a suggested 950 W PSU, while Intel specifies a 400 W TDP and a suggested 800 W PSU. This makes the Intel card more accessible for systems with lower power budgets. Physical dimensions also differ: NVIDIA measures 304 mm in length, 137 mm in height, and 48 mm in width; Intel measures 300 mm in length, 110 mm in height, and 40 mm in width. Both are dual-slot cards with a single 16-pin power connector.

Specification Differences

| Specification | Intel Arc Pro B60 Dual | NVIDIA GeForce RTX 5090 D |

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

| Chip | BMG-G21 | GB202 |

| Architecture | Xe2-HPG | Blackwell 2.0 |

| Generation | Battlemage (Pro Series) | GeForce 50 |

| Transistors | 19,600 million | 92,200 million |

| Die Size | 272 mm² | 750 mm² |

| Transistor Density | 72.1M / mm² | 122.9M / mm² |

| Base Clock | 2000 MHz | 2017 MHz |

| Boost Clock | 2400 MHz | 2407 MHz |

| Memory Clock | 2375 MHz (19 Gbps effective) | 1750 MHz (28 Gbps effective) |

| Memory Size | 24 GB | 32 GB |

| Memory Type | GDDR6 | GDDR7 |

| Memory Bus | 192 bit | 512 bit |

| Memory Bandwidth | 456.0 GB/s | 1.79 TB/s |

| Shading Units | 2560 | 21760 |

| TMUs | 160 | 680 |

| ROPs | 80 | 176 |

| RT Cores | 20 | 170 |

| Tensor Cores | N/A | 680 |

| Pixel Rate | 192.0 GPixel/s | 423.6 GPixel/s |

| Texture Rate | 384.0 GTexel/s | 1,636.8 GTexel/s |

| FP32 | 12.29 TFLOPS | 104.8 TFLOPS |

| FP16 | 24.58 TFLOPS (2:1) | 104.8 TFLOPS (1:1) |

| TDP | 400 W | 575 W |

| Suggested PSU | 800 W | 950 W |

| Bus Interface | PCIe 5.0 x8 | PCIe 5.0 x16 |

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

| Length | 300 mm | 304 mm |

| Height | 110 mm | 137 mm |

| Width | 40 mm | 48 mm |

| Release Date | 2025-09-04 | 2025-01-29 |

| Launch MSRP | 1,199 USD | 2,299 USD |

Head-to-Head Benchmarks

The database contains no head-to-head benchmark comparisons between these two GPUs. However, the NVIDIA GeForce RTX 5090 D has a full set of recorded benchmark scores, while the Intel Arc Pro B60 Dual has none. Therefore, the analysis of relative performance rests on the NVIDIA card's individual results and its position among nearest rivals.

The NVIDIA GeForce RTX 5090 D achieves a 3DMark Steel Nomad DX12 score of 14326. In Geekbench, it scores 310674 in OpenCL and 376915 in Vulkan. Passmark results show 44065 in G3D, 28396 in GPU Compute, 1487 in G2D, 434 in DirectX 9, 371 in DirectX 11, 231 in DirectX 10, and 219 in DirectX 12.

Comparing to its nearest rivals in the database, the RTX 5090 D sits 1.1% above the AMD Radeon RX 6650M XT (average score 76904), 1.6% below the AMD Radeon RX 6850M XT (average score 78940), 2.1% below the NVIDIA Tesla P100 PCIe 12 GB (average score 79396), and 2.4% below the NVIDIA Tesla P100 PCIe 16 GB (average score 79605). These delta percentages indicate that the RTX 5090 D's average benchmark score of 77712 places it in a tight cluster with these competitors, despite the vast architectural differences.

The Intel Arc Pro B60 Dual has no benchmark scores, no average score, and no nearest rivals listed. Its 50th percentile ranking suggests it sits near the median of all GPUs, but without recorded performance data, no direct numerical comparison can be made.

The Verdict

The data shows an overwhelming performance advantage for the NVIDIA GeForce RTX 5090 D. Its 92nd percentile ranking, average benchmark score of 77712, and extensive benchmark results confirm that it is built for high-end workloads. The 104.8 TFLOPS FP32 throughput, 104.8 TFLOPS FP16 throughput, 32 GB of GDDR7 memory, and 1.79 TB/s bandwidth place it in a category far above the Intel Arc Pro B60 Dual.

The Intel Arc Pro B60 Dual, by contrast, sits at the 50th percentile with no recorded benchmark scores. Its 24 GB of GDDR6 memory, 12.29 TFLOPS FP32, and 456.0 GB/s bandwidth indicate a more modest compute envelope. The 400 W TDP and 800 W suggested PSU make it a lighter power load, and the 300 mm length fits in similar physical space as NVIDIA's 304 mm card. The Intel card's 4x mini-DisplayPort 2.1 outputs may suit professional display configurations, while NVIDIA offers 1x HDMI 2.1b and 3x DisplayPort 2.1b.

For users prioritizing raw compute, memory bandwidth, and ray tracing capability, the NVIDIA GeForce RTX 5090 D is the clear choice based on recorded data. For users needing a dual-slot GPU with lower power demands and a smaller footprint, the Intel Arc Pro B60 Dual presents a viable alternative, though its performance remains unquantified in the database. The release timing also differs: NVIDIA shipped on 2025-01-29, while Intel arrived on 2025-09-04. The launch MSRP of 2,299 USD for NVIDIA versus 1,199 USD for Intel reflects the performance gap, but the Intel card's lack of benchmark data means its actual capability is unverified.