Intel Arc Pro B390 vs NVIDIA GeForce RTX 5090 Comparison

FAQ

Q: What are the core architectural differences between the Intel Arc Pro B390 and the NVIDIA GeForce RTX 5090?

A: The Intel Arc Pro B390 uses the Xe3-LPG architecture on a 3 nm process with 1,536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores. The RTX 5090 uses Blackwell 2.0 on a 5 nm TSMC process with 21,760 shading units, 680 TMUs, 176 ROPs, 170 ray tracing cores, and 680 tensor cores.

Q: How do the memory configurations compare?

A: The Arc Pro B390 uses system-shared memory with system-dependent bandwidth and no dedicated VRAM. The RTX 5090 has 32 GB of GDDR7 on a 512-bit bus, delivering 1.79 TB/s of bandwidth at 1750 MHz (28 Gbps effective).

Q: Which GPU has a higher benchmark percentile ranking?

A: The RTX 5090 sits at the 92nd percentile among all GPUs, while the Arc Pro B390 is at the 50th percentile. The RTX 5090's average benchmark score is 79,842, whereas the Arc Pro B390 has no recorded benchmark scores in the database.

Q: What are the power consumption figures?

A: The Arc Pro B390 has a TDP of 80 W with no power connectors and an integrated graphics processor (IGP) slot width. The RTX 5090 has a 575 W TDP, requires a single 16-pin power connector, and recommends a 950 W power supply.

Q: What display outputs does each GPU support?

A: The Arc Pro B390's display outputs are listed as portable device dependent. The RTX 5090 provides 1x HDMI 2.1b and 3x DisplayPort 2.1b outputs.

Q: What are the release dates and form factors?

A: The Arc Pro B390 released on January 26, 2026, as an IGP with no slot width beyond integrated. The RTX 5090 released on January 29, 2025, as a dual-slot card measuring 304 mm x 137 mm x 40 mm.

Architecture Differences

The Intel Arc Pro B390 is built on Intel's 3 nm process using the Xe3-LPG architecture, which is part of the Arc Graphics-WM (Panther Lake) generation. The chip runs at a base clock of 300 MHz and a boost clock of 2500 MHz. Its compute configuration includes 1,536 shading units, 48 texture mapping units, 24 raster operation units, and 12 ray tracing cores. The FP32 throughput is 7.680 TFLOPS, with FP16 rated at 15.36 TFLOPS at a 2:1 ratio. Pixel rate is 60.00 GPixel/s, and texture rate is 120.0 GTexel/s. The GPU relies entirely on system-shared memory, meaning its memory size, type, bus width, and bandwidth are all system dependent. It is an integrated part of the Panther Lake package with an IGP bus interface, consumes 80 W, and requires no external power connectors.

The NVIDIA GeForce RTX 5090 uses the Blackwell 2.0 architecture on TSMC's 5 nm process. The GB202 chip contains 92,200 million transistors on a 750 mm² die, giving a transistor density of 122.9M per mm². Base clock is 2017 MHz with a boost of 2407 MHz. The GPU has 21,760 shading units, 680 TMUs, 176 ROPs, 170 ray tracing cores, and 680 tensor cores. FP32 performance reaches 104.8 TFLOPS, and FP16 also hits 104.8 TFLOPS at a 1:1 ratio. Pixel rate is 423.6 GPixel/s, and texture rate is 1,636.8 GTexel/s. Memory is 32 GB of GDDR7 on a 512-bit bus, providing 1.79 TB/s bandwidth. The card is dual-slot, uses PCIe 5.0 x16, has a 575 W TDP, and requires a 1x 16-pin power connector with a suggested 950 W PSU.

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Arc Pro B390 has no tensor cores listed, while the RTX 5090 includes 680 tensor cores for AI acceleration. The Intel part is an integrated solution with no dedicated cooling or expansion slot requirements, whereas the RTX 5090 is a discrete dual-slot card with physical dimensions of 304 mm in length, 137 mm in height, and 40 mm in width.

The Verdict

Based on recorded data, the NVIDIA GeForce RTX 5090 is the clear performance leader. Its 92nd percentile ranking versus the Arc Pro B390's 50th percentile shows a massive gap in overall GPU capability. The RTX 5090 has 10 benchmark scores in the database, including a Passmark G3D score of 39,650, a Geekbench OpenCL score of 334,370, and a Geekbench Vulkan score of 376,728. The Arc Pro B390 has no benchmark scores recorded, making direct performance comparison impossible from measurements.

The RTX 5090 also holds advantages in raw compute resources: 14.2 times more shading units, 14.2 times more TMUs, 7.3 times more ROPs, and 14.2 times more ray tracing cores. Its FP32 throughput is 13.6 times higher, and its pixel rate is 7.1 times higher. The 32 GB GDDR7 memory with 1.79 TB/s bandwidth is a dedicated high-speed configuration, whereas the Arc Pro B390 relies on shared system memory.

The Arc Pro B390 is suitable for systems where integrated graphics are sufficient. Its 80 W TDP, IGP form factor, and lack of power connectors make it a low-power integrated option. The RTX 5090, by contrast, is designed for maximum discrete performance with a 575 W TDP and a 950 W suggested PSU. Users requiring dedicated VRAM, high-bandwidth memory, or tensor core acceleration should select the RTX 5090. Users needing a power-efficient integrated GPU for basic display tasks would choose the Arc Pro B390.

The RTX 5090's nearest rivals in the database are the NVIDIA Tesla P100 PCIe 16 GB with an average score of 79,605 (0.3% behind), the NVIDIA Tesla P100 PCIe 12 GB at 79,396 (0.6% behind), the AMD Radeon RX 6850M XT at 78,940 (1.1% behind), and the AMD Radeon Pro Vega 64X at 80,959 (1.4% ahead). The Arc Pro B390 has no nearest rivals listed.

Specification Differences

| Specification | Intel Arc Pro B390 | NVIDIA GeForce RTX 5090 |

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

| 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 | null | 122.9M / mm² |

| Base Clock | 300 MHz | 2017 MHz |

| Boost Clock | 2500 MHz | 2407 MHz |

| Memory Size | System Shared | 32 GB |

| Memory Type | System Shared | GDDR7 |

| Memory Bus Width | System Shared | 512 bit |

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

| Memory Clock | System Shared | 1750 MHz, 28 Gbps effective |

| Shading Units | 1536 | 21760 |

| TMUs | 48 | 680 |

| ROPs | 24 | 176 |

| Ray Tracing Cores | 12 | 170 |

| Tensor Cores | null | 680 |

| Pixel Rate | 60.00 GPixel/s | 423.6 GPixel/s |

| Texture Rate | 120.0 GTexel/s | 1,636.8 GTexel/s |

| FP32 | 7.680 TFLOPS | 104.8 TFLOPS |

| FP16 | 15.36 TFLOPS (2:1) | 104.8 TFLOPS (1:1) |

| TDP | 80 W | 575 W |

| Slot Width | IGP | Dual-slot |

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

| Suggested PSU | null | 950 W |

| Bus Interface | IGP | PCIe 5.0 x16 |

| Display Outputs | Portable Device Dependent | 1x HDMI 2.1b, 3x DisplayPort 2.1b |

| Dimensions | null | 304 mm x 137 mm x 40 mm |

| Release Date | 2026-01-26 | 2025-01-29 |

| Predecessor | HD Graphics-WM | GeForce 40 |

| Successor | null | GeForce 60 |

| Launch MSRP | null | 1,999 USD |

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark comparisons between the Arc Pro B390 and the RTX 5090. The Arc Pro B390 has zero recorded benchmark scores, while the RTX 5090 has ten individual scores across multiple test suites.

The RTX 5090's strongest measured results include a 3DMark Steel Nomad DX12 score of 18,355, a Geekbench OpenCL score of 334,370, and a Geekbench Vulkan score of 376,728. In Passmark tests, it scores 226 in DirectX 10, 341 in DirectX 11, 185 in DirectX 12, 395 in DirectX 9, 1,413 in G2D, 39,650 in G3D, and 26,756 in GPU compute. The average benchmark score across all tests is 79,842.

The RTX 5090's nearest rival comparisons show narrow margins: it is 0.3% ahead of the Tesla P100 PCIe 16 GB, 0.6% ahead of the Tesla P100 PCIe 12 GB, and 1.1% ahead of the AMD Radeon RX 6850M XT. The AMD Radeon Pro Vega 64X sits 1.4% ahead of the RTX 5090 in average score.

Since the Arc Pro B390 has no benchmark data, the only quantitative comparison comes from specifications. The RTX 5090 delivers 13.6 times the FP32 throughput, 7.1 times the pixel rate, and 13.6 times the texture rate. The RTX 5090's memory bandwidth of 1.79 TB/s versus system-dependent shared memory for the Arc Pro B390 represents a fundamental advantage in memory-intensive workloads.

The RTX 5090's 92nd percentile ranking places it among the top GPUs in the database. The Arc Pro B390's 50th percentile with an average benchmark score of 0 indicates no recorded performance data, making any performance claims about the Intel part speculative. The wins tally confirms this: the RTX 5090 has no recorded wins in head-to-head tests, and the Arc Pro B390 also has zero wins, reflecting the absence of direct comparisons.