GPU Comparison

The NVIDIA RTX 5000 Mobile Ada Generation and the Intel Arc Pro B60 are two very different approaches to professional graphics, and the benchmark data reflects that starkly. In the single shared 3DMark Steel Nomad DX12 test, the NVIDIA part posts a score of 3596, which is a decisive 35.9% ahead of the Intel card's 2646. However, this does not tell the whole story, as the Intel Arc Pro B60 brings a significantly larger memory pool and a different architectural focus to the table. The data indicates these are specialized tools rather than direct competitors, with the NVIDIA GPU excelling in raw rendering throughput while the Intel card offers a distinct set of capabilities for specific professional workloads.

Head-to-Head Benchmarks

The only directly comparable benchmark between the two is the 3DMark Steel Nomad DX12 test, and the results are heavily skewed. The NVIDIA RTX 5000 Mobile Ada Generation scores 3596, while the Intel Arc Pro B60 scores 2646. This translates to a 35.9% performance advantage for the NVIDIA solution in this specific DirectX 12 workload. The NVIDIA GPU’s percentile ranking among all GPUs is 21, while the Intel card sits just one point lower at 20, but the delta in raw score is substantial. It is worth noting that the Intel Arc Pro B60’s nearest rival by average benchmark score is the NVIDIA Quadro P1000 at 3163, which the Intel card trails by a mere 0.6%, while the RTX 5000 Mobile Ada’s closest competitor is the NVIDIA GeForce GT 545 at 3594, which it edges out by only 0.1%.

The Intel Arc Pro B60 has additional benchmark data from PassMark that the NVIDIA card lacks, which shows a different performance profile. In PassMark G3D, the Intel card scores 14580, and in GPU Compute it scores 7029. Its DirectX 9 performance is particularly strong at 179, a notably higher score than its DirectX 10 (61), DirectX 11 (122), or DirectX 12 (76) results. This suggests the Intel architecture has varying strengths depending on the API generation, which is a key consideration for legacy application support. The NVIDIA card, by contrast, only has the one 3DMark result in the data, making a broader comparison impossible, but its single score is enough to establish a clear lead in modern, high-end rendering tasks.

Architecture Differences

The two GPUs are built on fundamentally different architectural philosophies. The NVIDIA RTX 5000 Mobile Ada Generation uses the AD103 chip based on the Ada Lovelace architecture, manufactured on a 5 nm process at TSMC with a massive 45,900 million transistors on a 379 mm² die. This results in a transistor density of 121.1M per mm². In contrast, the Intel Arc Pro B60 uses the BMG-G21 chip based on the Xe2-HPG architecture, also on a 5 nm TSMC process, but with only 19,600 million transistors on a 272 mm² die, giving it a lower density of 72.1M per mm².

The compute resources differ dramatically. The NVIDIA GPU boasts 9728 shading units, 304 TMUs, and 112 ROPs, alongside 76 RT cores and 304 tensor cores. The Intel card has only 2560 shading units, 160 TMUs, and 80 ROPs, with 20 RT cores and no listed tensor cores. This massive difference in shader count is the primary driver of the NVIDIA card’s higher raw FP32 performance of 41.15 TFLOPS compared to the Intel card’s 12.29 TFLOPS. The Intel card does have a 2:1 FP16 ratio, delivering 24.58 TFLOPS, while the NVIDIA card offers a 1:1 FP16 rate at 41.15 TFLOPS. The NVIDIA GPU also leads in pixel and texture rates, with 236.9 GPixel/s and 643.0 GTexel/s versus the Intel card’s 192.0 GPixel/s and 384.0 GTexel/s.

Memory configuration is another point of divergence. The NVIDIA RTX 5000 Mobile Ada Generation uses 16 GB of GDDR6 on a 256-bit bus, achieving a bandwidth of 576.0 GB/s. The Intel Arc Pro B60 offers a larger 24 GB frame buffer, but on a narrower 192-bit bus, resulting in lower bandwidth of 456.0 GB/s. The Intel card’s memory clock is slightly higher at 2375 MHz (19 Gbps effective) compared to the NVIDIA card’s 2250 MHz (18 Gbps effective), but the wider bus on the NVIDIA card still provides superior overall bandwidth. Power and physical specifications also differ, with the NVIDIA card being an IGP with no power connectors and a 120 W TDP, while the Intel card is a dual-slot design requiring a single 8-pin connector and a 550 W suggested PSU, with a 200 W TDP.

Where Each One Wins

The NVIDIA RTX 5000 Mobile Ada Generation wins decisively in raw graphics compute. Its 35.9% lead in the 3DMark Steel Nomad DX12 benchmark, combined with its superior FP32 throughput and higher memory bandwidth, makes it the clear choice for tasks that demand maximum rendering performance, such as high-resolution 3D modeling, complex visual effects, and real-time ray tracing in modern applications. The presence of 304 tensor cores also indicates a strong capability for AI-accelerated workloads, although no specific benchmark data is provided for that. The NVIDIA card’s higher texture and pixel rates make it particularly well-suited for filling large frame buffers with complex scenes.

The Intel Arc Pro B60, while slower in raw compute, has its own advantages. Its 24 GB memory capacity is 50% larger than the NVIDIA card’s 16 GB, which is a significant benefit for workloads that require massive datasets to reside in video memory, such as large-scale data visualization, certain scientific simulations, or working with extremely high-resolution textures and geometry. The PassMark results show the Intel card has strong performance in legacy DirectX 9 applications, scoring 179, which could be relevant for older professional software that has not been updated. Its lower FP32 performance is a trade-off, but the larger memory pool addresses a different bottleneck entirely. The Intel card’s dual-slot design and active cooling solution, implied by its 200 W TDP, also make it a more conventional add-in card compared to the mobile-oriented NVIDIA IGP.

FAQ

Q: Which GPU has a higher score in 3DMark Steel Nomad DX12?

A: The NVIDIA RTX 5000 Mobile Ada Generation scores 3596, which is 35.9% higher than the Intel Arc Pro B60's score of 2646.

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

A: The Intel Arc Pro B60 has 24 GB of GDDR6 memory, while the NVIDIA RTX 5000 Mobile Ada Generation has 16 GB of GDDR6 memory.

Q: What is the transistor count difference?

A: The NVIDIA GPU has 45,900 million transistors, whereas the Intel GPU has 19,600 million transistors.

Q: Which card has a higher boost clock speed?

A: The Intel Arc Pro B60 has a boost clock of 2400 MHz, which is higher than the NVIDIA RTX 5000 Mobile Ada Generation's boost clock of 2115 MHz.

Q: What is the power consumption for each card?

A: The NVIDIA RTX 5000 Mobile Ada Generation has a TDP of 120 W, while the Intel Arc Pro B60 has a TDP of 200 W.

Q: How do their average benchmark scores compare?

A: The NVIDIA RTX 5000 Mobile Ada Generation has an average benchmark score of 3596, while the Intel Arc Pro B60 has an average score of 3182.

The Verdict

The data points to a clear split in purpose. The NVIDIA RTX 5000 Mobile Ada Generation is the performance leader. Its 35.9% advantage in the primary 3DMark benchmark and its superior compute specifications make it the obvious choice for users who prioritize maximum frame rates and rendering speed. The benchmark results indicate that for any modern, demanding DirectX 12 workload, the NVIDIA card will deliver significantly better performance. If your priority is raw speed and you do not need more than 16 GB of memory, the NVIDIA card is the stronger pick based on the available data.

The Intel Arc Pro B60 is for a different user. Its 24 GB memory capacity is its most compelling feature, offering 8 GB more than the NVIDIA card. This makes it a more practical option for professionals who are memory-limited rather than compute-limited. The PassMark data also suggests it has strong legacy DirectX 9 performance. The benchmark results indicate that if your workflow requires holding very large datasets in GPU memory, the Intel card’s larger frame buffer could be a deciding factor, despite its lower overall compute performance. The data shows a trade-off between speed and capacity, with the NVIDIA card winning on the former and the Intel card on the latter.

Specification Differences

| Specification | NVIDIA RTX 5000 Mobile Ada Generation | Intel Arc Pro B60 |

| :--- | :--- | :--- |

| Chip | AD103 | BMG-G21 |

| Architecture | Ada Lovelace | Xe2-HPG |

| Generation | Ada-MW | Battlemage (Pro Series) |

| Transistors | 45,900 million | 19,600 million |

| Die Size | 379 mm² | 272 mm² |

| Transistor Density | 121.1M / mm² | 72.1M / mm² |

| Base Clock | 1425 MHz | 2000 MHz |

| Boost Clock | 2115 MHz | 2400 MHz |

| Memory Size | 16 GB | 24 GB |

| Memory Bus Width | 256 bit | 192 bit |

| Memory Bandwidth | 576.0 GB/s | 456.0 GB/s |

| Shading Units | 9728 | 2560 |

| TMUs | 304 | 160 |

| ROPs | 112 | 80 |

| RT Cores | 76 | 20 |

| Tensor Cores | 304 | null |

| Pixel Rate | 236.9 GPixel/s | 192.0 GPixel/s |

| Texture Rate | 643.0 GTexel/s | 384.0 GTexel/s |

| FP32 Performance | 41.15 TFLOPS | 12.29 TFLOPS |

| FP16 Performance | 41.15 TFLOPS (1:1) | 24.58 TFLOPS (2:1) |

| TDP | 120 W | 200 W |

| Slot Width | IGP | Dual-slot |

| Power Connectors | None | 1x 8-pin |

| Suggested PSU | null | 550 W |

| Bus Interface | PCIe 4.0 x16 | PCIe 5.0 x8 |

| Display Outputs | Portable Device Dependent | 4x mini-DisplayPort 2.1 |

| Dimensions (LxHxW) | null | 167 mm x 69 mm x 40 mm |

| Release Date | 2023-03-20 | 2025-09-04 |

| Launch MSRP | null | 499 USD |