Intel Arc B390 vs NVIDIA RTX PRO 6000 Blackwell Max-Q Comparison

Head-to-Head Benchmarks

The recorded data contains a single direct comparison between the Intel Arc B390 and the NVIDIA RTX PRO 6000 Blackwell Max-Q, using the 3DMark Steel Nomad DX12 test. The NVIDIA part wins this benchmark decisively, scoring 11088 points against the Intel part’s 1482 points. The delta is recorded at -86.6 percent from the perspective of the Intel Arc B390, meaning the Intel solution trails by that margin in this workload.

To contextualize the Intel Arc B390’s score, the database places it at the 9th percentile among all GPUs. Its nearest rivals in the database are all older, low-end NVIDIA parts: the GeForce GT 520MX with an average score of 1463 (delta of 1.3 percent), the GeForce 800M at 1460 (1.5 percent), the GeForce GT 625 OEM at 1446 (2.5 percent), and the GeForce GT 710 at 1443 (2.7 percent). The Arc B390’s 1482 points places it just ahead of all four, but the margins are narrow, ranging from 1.3 to 2.7 percent. This indicates that in this benchmark, the Arc B390 performs in the same tier as those decade-old discrete mobile and entry-level desktop parts, rather than delivering a modern integrated GPU advantage.

The NVIDIA RTX PRO 6000 Blackwell Max-Q, by contrast, sits at the 50th percentile among all GPUs. Its nearest rivals include the RTX PRO 6000D Blackwell Max-Q with an identical average score of 11088 (delta of 0 percent), the AMD Radeon RX 550 at 11075 (0.1 percent), the GeForce GTX 1650 SUPER at 11047 (0.4 percent), and the AMD FirePro W4300 at 11225, which actually scores higher by 1.2 percent. The RTX PRO 6000 Blackwell Max-Q effectively ties with those parts in this test, despite the massive architectural and specification differences between them. The data shows that the NVIDIA card’s raw score is 7.48 times higher than the Intel Arc B390’s score, a gap that dwarfs any of the intra-tier differences recorded for either product.

The benchmark’s winner tally confirms the sweep: the Intel part records zero wins, while the NVIDIA part records one win. The single data point is sufficient to establish a clear performance hierarchy in this specific DX12 test, but it does not provide evidence for how either GPU behaves in other workloads, such as compute, ray tracing, or power-limited scenarios.

Architecture Differences

The two GPUs come from entirely different design philosophies and manufacturing contexts. The Intel Arc B390 is built on a 3 nm process node at Intel’s foundry, using the Panther Lake chip with the Xe3-LPG architecture. It belongs to the Arc Graphics-M (Panther Lake) generation. The NVIDIA RTX PRO 6000 Blackwell Max-Q uses the GB202 chip with the Blackwell 2.0 architecture, fabricated on a 5 nm node at TSMC. Its generation is listed as Blackwell PRO W (x000). The process node difference (3 nm versus 5 nm) is notable, but the Intel part is an integrated graphics processor (IGP), while the NVIDIA part is a discrete, dual-slot expansion card.

Transistor counts and die sizes diverge sharply. The Intel Arc B390 has an unknown transistor count and die size. The NVIDIA part has 92,200 million transistors on a 750 mm² die, yielding a transistor density of 122.9 million per mm². This is the only die-level quantitative data available, and it reflects the NVIDIA card’s status as a large, high-power discrete GPU. The Intel part’s IGP nature means its transistors are shared with the host processor, but the database does not record those figures.

Core configurations reveal the scale of the performance gap. The Intel Arc B390 has 1536 shading units, 48 texture mapping units (TMUs), and 24 render output units (ROPs). It also includes 12 ray tracing cores. The NVIDIA RTX PRO 6000 Blackwell Max-Q has 24064 shading units, 752 TMUs, 192 ROPs, and 188 ray tracing cores. Additionally, the NVIDIA part includes 752 tensor cores, a feature the Intel part does not list. The shading unit count alone is 15.7 times higher on the NVIDIA side, which aligns with the benchmark score ratio.

Clock speeds follow different patterns. The Intel Arc B390 has a base clock of 300 MHz and a boost clock of 2500 MHz. The NVIDIA part has a base clock of 1035 MHz and a boost clock of 2280 MHz. The Intel part’s boost clock is higher than the NVIDIA part’s boost clock, but the NVIDIA part’s base clock is substantially higher. The NVIDIA card also has a dedicated memory clock of 1750 MHz (28 Gbps effective), while the Intel part’s memory clock is listed as “System Shared,” meaning it relies on system memory with no dedicated clock.

Memory configurations are fundamentally different. The Intel Arc B390 uses system-shared memory with a system-shared bus width and system-dependent bandwidth. The NVIDIA RTX PRO 6000 Blackwell Max-Q has 96 GB of GDDR7 memory on a 512-bit bus, delivering 1.79 TB/s of bandwidth. This is a dedicated, high-capacity memory subsystem versus the Intel part’s dependence on the host system’s memory. The Intel part’s bandwidth is explicitly recorded as “System Dependent,” so no fixed number can be compared.

The NVIDIA card also features a PCIe 5.0 x16 bus interface, while the Intel part uses an integrated graphics processor interface (IGP) with no separate bus. The NVIDIA card is dual-slot, measures 267 mm in length, 111 mm in height, and 40 mm in width, and uses a single 16-pin power connector. The Intel part is an IGP with no slot width, no power connectors, and no dimensions recorded. Display outputs differ as well: the NVIDIA card has 4x DisplayPort 2.1b, while the Intel part’s outputs are listed as “Portable Device Dependent,” reflecting its mobile integrated nature.

Both parts support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The NVIDIA part’s FP16 throughput is 109.7 TFLOPS at a 1:1 ratio with FP32, while the Intel part’s FP16 is 15.36 TFLOPS at a 2:1 ratio. The NVIDIA card’s FP32 is also 109.7 TFLOPS versus the Intel part’s 7.680 TFLOPS. Pixel and texture rates follow the same trend: the NVIDIA card delivers 437.8 GPixel/s and 1,714.6 GTexel/s, while the Intel part delivers 60.00 GPixel/s and 120.0 GTexel/s.

The Verdict

The data provides a single benchmark result, and that result is unambiguous. The NVIDIA RTX PRO 6000 Blackwell Max-Q outscores the Intel Arc B390 by 86.6 percent in 3DMark Steel Nomad DX12. The NVIDIA part’s score of 11088 places it at the 50th percentile, while the Intel part’s 1482 places it at the 9th percentile. For any workload represented by this DX12 test, the NVIDIA card is the clear choice.

However, the two products serve different roles. The Intel Arc B390 is an integrated GPU with an 80 W TDP, no power connectors, and system-shared memory. It is designed for portable devices, as indicated by its display output description. The NVIDIA RTX PRO 6000 Blackwell Max-Q is a 300 W discrete workstation card with a 700 W suggested power supply, 96 GB of dedicated GDDR7 memory, and a dual-slot form factor. The Intel part has a launch MSRP of none, while the NVIDIA part has a launch MSRP of 8,565 USD.

From the recorded data, the NVIDIA card wins the only benchmark, has 15.7 times the shading units, 15.7 times the TMUs, 8 times the ROPs, and 15.7 times the ray tracing cores. It also has 7.48 times the FP32 throughput and 7.14 times the FP16 throughput. The Intel part’s only advantages are its lower TDP (80 W versus 300 W), its higher boost clock (2500 MHz versus 2280 MHz), and its integrated nature, which requires no additional slot or power connectors. The Intel part’s boost clock advantage does not translate into a benchmark win, indicating that the NVIDIA card’s massive core count and memory bandwidth dominate despite a lower boost frequency.

FAQ

Q: Which GPU scores higher in 3DMark Steel Nomad DX12?

A: The NVIDIA RTX PRO 6000 Blackwell Max-Q scores 11088, while the Intel Arc B390 scores 1482. The NVIDIA part wins with a delta of -86.6 percent from the Intel part’s perspective.

Q: How does the Intel Arc B390 compare to its nearest rivals in the database?

A: The Arc B390 scores 1482, which is 1.3 percent ahead of the GeForce GT 520MX (1463), 1.5 percent ahead of the GeForce 800M (1460), 2.5 percent ahead of the GeForce GT 625 OEM (1446), and 2.7 percent ahead of the GeForce GT 710 (1443).

Q: What are the memory specifications for each GPU?

A: The Intel Arc B390 uses system-shared memory with system-dependent bandwidth. The NVIDIA RTX PRO 6000 Blackwell Max-Q has 96 GB of GDDR7 memory on a 512-bit bus with 1.79 TB/s bandwidth.

Q: What is the power consumption difference?

A: The Intel Arc B390 has a TDP of 80 W and no power connectors. The NVIDIA RTX PRO 6000 Blackwell Max-Q has a TDP of 300 W, uses a single 16-pin power connector, and has a suggested power supply of 700 W.

Q: Which GPU has more ray tracing cores?

A: The NVIDIA RTX PRO 6000 Blackwell Max-Q has 188 ray tracing cores, while the Intel Arc B390 has 12 ray tracing cores.

Q: Do both GPUs support the same graphics APIs?

A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Where Each One Wins

The NVIDIA RTX PRO 6000 Blackwell Max-Q wins the only recorded benchmark, the 3DMark Steel Nomad DX12 test, by a score of 11088 to 1482. This is the sole head-to-head data point, and it shows a 86.6 percent advantage for the NVIDIA card. The NVIDIA card also wins on every recorded compute and memory metric: FP32 (109.7 TFLOPS versus 7.680 TFLOPS), FP16 (109.7 TFLOPS versus 15.36 TFLOPS), pixel rate (437.8 GPixel/s versus 60.00 GPixel/s), texture rate (1,714.6 GTexel/s versus 120.0 GTexel/s), memory capacity (96 GB versus system shared), and memory bandwidth (1.79 TB/s versus system dependent). It also has more shading units, TMUs, ROPs, ray tracing cores, and tensor cores.

The Intel Arc B390 wins on power efficiency as recorded by TDP: 80 W versus 300 W. It also has a higher boost clock at 2500 MHz versus 2280 MHz, and it requires no external power connectors, no slot width, and no separate bus interface. Its display outputs are portable-device dependent, which means it is designed for integration into mobile systems. The NVIDIA card requires a dual-slot form factor, a 16-pin power connector, and a 700 W power supply, making it unsuitable for the same portable contexts. For a system where power draw and physical footprint are the primary constraints, the Intel part holds the advantage, but the NVIDIA card dominates in raw performance and feature set.

Specification Differences

| Specification | Intel Arc B390 | NVIDIA RTX PRO 6000 Blackwell Max-Q |

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

| Chip | Panther Lake | GB202 |

| Architecture | Xe3-LPG | Blackwell 2.0 |

| Process Node | 3 nm | 5 nm |

| Foundry | Intel | TSMC |

| Transistors | Unknown | 92,200 million |

| Die Size | Unknown | 750 mm² |

| Transistor Density | Not recorded | 122.9M / mm² |

| Base Clock | 300 MHz | 1035 MHz |

| Boost Clock | 2500 MHz | 2280 MHz |

| Memory Clock | System Shared | 1750 MHz (28 Gbps effective) |

| Memory Size | System Shared | 96 GB |

| Memory Type | System Shared | GDDR7 |

| Memory Bus Width | System Shared | 512 bit |

| Memory Bandwidth | System Dependent | 1.79 TB/s |

| Shading Units | 1536 | 24064 |

| TMUs | 48 | 752 |

| ROPs | 24 | 192 |

| Ray Tracing Cores | 12 | 188 |

| Tensor Cores | Not recorded | 752 |

| Pixel Rate | 60.00 GPixel/s | 437.8 GPixel/s |

| Texture Rate | 120.0 GTexel/s | 1,714.6 GTexel/s |

| FP32 Performance | 7.680 TFLOPS | 109.7 TFLOPS |

| FP16 Performance | 15.36 TFLOPS (2:1) | 109.7 TFLOPS (1:1) |

| TDP | 80 W | 300 W |

| Slot Width | IGP | Dual-slot |

| Power Connectors | None | 1x 16-pin |

| Suggested PSU | Not recorded | 700 W |

| Bus Interface | IGP | PCIe 5.0 x16 |

| Display Outputs | Portable Device Dependent | 4x DisplayPort 2.1b |

| Dimensions | Not recorded | 267 mm length, 111 mm height, 40 mm width |

| Release Date | 2026-01-26 | 2025-03-17 |