Intel Arc B390 vs NVIDIA GeForce RTX 5090 Comparison

Head-to-Head Benchmarks

The recorded data contains a single direct comparison between the Intel Arc B390 and the NVIDIA GeForce RTX 5090: the 3DMark Steel Nomad DX12 test. In this workload, the RTX 5090 scores 18,355 points, while the Arc B390 manages 1,482 points. That places the NVIDIA part 91.9% ahead, a decisive margin that reflects the fundamental difference in positioning between these two products.

The RTX 5090’s nearest rivals in the database help contextualize its score. It sits 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 only listed competitor that beats it is the AMD Radeon Pro Vega 64X, which leads by 1.4%. This places the RTX 5090 in the 92nd percentile of all GPUs in the database, meaning it outperforms the vast majority of recorded graphics hardware.

For the Arc B390, the same benchmark places it in the 9th percentile of all GPUs. Its nearest rivals are all low-end NVIDIA parts: the GeForce GT 520MX (1.3% ahead), the GeForce 800M (1.5% ahead), the GeForce GT 625 OEM (2.5% ahead), and the GeForce GT 710 (2.7% ahead). The Arc B390 trails all four, but only by a small margin. This shows that while it is not competitive with the RTX 5090, it is also not dramatically slower than the entry-level discrete GPUs it is grouped with.

The delta of 91.9% in the head-to-head test is the only direct measurement available. No other overlapping benchmark results exist between the two products. The RTX 5090 has additional scores in Geekbench OpenCL, Geekbench Vulkan, and several Passmark tests, but the Arc B390 has no corresponding entries for those workloads. The analysis below therefore relies on the single shared test plus the architectural and specification data recorded for each part.

The Verdict

The data indicates two products with entirely different performance envelopes. The RTX 5090 delivers a 3DMark Steel Nomad score of 18,355, which places it in the 92nd percentile. The Arc B390 delivers 1,482 points, placing it in the 9th percentile. The RTX 5090 is 91.9% faster in this test, with no overlap in their benchmark distributions.

The RTX 5090 is a discrete, dual-slot add-in card with a 575 W TDP and a 950 W suggested power supply. It uses a PCIe 5.0 x16 interface and requires a single 16-pin power connector. The Arc B390 is an integrated graphics processor (IGP) with an 80 W TDP, no power connectors, and a bus interface listed simply as IGP. It shares system memory, while the RTX 5090 has 32 GB of dedicated GDDR7 VRAM on a 512-bit bus.

For anyone selecting between these two, the RTX 5090 is the only option for high-end rendering workloads. Its nearest rivals are all professional or high-end mobile parts, and it holds its own against them. The Arc B390 is grouped with decade-old entry-level GPUs like the GeForce GT 710, and its performance reflects that tier. The choice is not about preference; it is about whether the workload requires the RTX 5090’s capabilities.

The production status for both is listed as Active, with the RTX 5090 released on 2025-01-29 and the Arc B390 released on 2026-01-26. The RTX 5090 has a recorded launch MSRP of 1,999 USD. The Arc B390 has no launch MSRP recorded.

Where Each One Wins

The RTX 5090 wins the only directly comparable benchmark, and it does so by a wide margin. In 3DMark Steel Nomad DX12, it scores 18,355 versus 1,482 for the Arc B390. That is the sole recorded win for either product.

Beyond that single test, the RTX 5090 shows strength in other recorded workloads that the Arc B390 does not share. Its Geekbench OpenCL score is 334,370, its Geekbench Vulkan score is 376,728, and its Passmark G3D score is 39,650. The Passmark G2D score of 1,413 and GPU compute score of 26,756 further indicate broad capability across different rendering and compute APIs.

The Arc B390 has no other benchmark entries in the database. Its only recorded result is the 3DMark Steel Nomad score. This means there is no data to suggest any workload where it outperforms the RTX 5090. The architecture differences, covered below, do not indicate any advantage that would overturn the benchmark result.

For use-case planning, the RTX 5090 is suited to tasks that stress pixel throughput, texture mapping, and compute. Its pixel rate is 423.6 GPixel/s and texture rate is 1,636.8 GTexel/s. The Arc B390 delivers 60.00 GPixel/s and 120.0 GTexel/s. In every measurable metric where both have data, the RTX 5090 leads.

FAQ

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

A: The NVIDIA GeForce RTX 5090 scores 18,355, while the Intel Arc B390 scores 1,482. The RTX 5090 is 91.9% faster in this test.

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

A: The Arc B390 trails all four of its nearest rivals in the database. The GeForce GT 520MX is 1.3% faster, the GeForce 800M is 1.5% faster, the GeForce GT 625 OEM is 2.5% faster, and the GeForce GT 710 is 2.7% faster.

Q: What is the RTX 5090’s position relative to similar GPUs?

A: It sits in the 92nd percentile of all GPUs. Among its nearest rivals, 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 is 1.4% faster.

Q: Does the Arc B390 have any benchmark wins over the RTX 5090?

A: No. The only shared benchmark is 3DMark Steel Nomad DX12, which the RTX 5090 wins. The database records zero wins for the Arc B390 in head-to-head comparisons.

Q: What memory configuration does each GPU use?

A: The RTX 5090 has 32 GB of GDDR7 memory on a 512-bit bus with 1.79 TB/s bandwidth. The Arc B390 uses system shared memory with a system-dependent bandwidth.

Q: What are the power requirements for each card?

A: The RTX 5090 has a 575 W TDP, requires a 950 W suggested power supply, and uses one 16-pin connector. The Arc B390 has an 80 W TDP, no power connectors, and is an integrated processor.

Architecture Differences

The two GPUs use fundamentally different architectures and manufacturing processes. The Intel Arc B390 is built on the Xe3-LPG architecture using the Panther Lake chip, fabricated on a 3 nm process at Intel’s own foundry. The NVIDIA GeForce RTX 5090 uses the Blackwell 2.0 architecture with the GB202 chip, fabricated on a 5 nm process at TSMC.

Transistor counts differ dramatically. The RTX 5090 has 92,200 million transistors on a 750 mm² die, giving a density of 122.9 million transistors per square millimeter. The Arc B390’s transistor count and die size are listed as unknown, so no direct comparison is possible.

The RTX 5090 has 21,760 shading units, 680 texture mapping units, 176 ROPs, 170 ray tracing cores, and 680 tensor cores. The Arc B390 has 1,536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores. It has no recorded tensor core count.

Pixel and texture rates reflect the resource gap. The RTX 5090 outputs 423.6 GPixel/s and 1,636.8 GTexel/s. The Arc B390 outputs 60.00 GPixel/s and 120.0 GTexel/s. Floating point performance follows the same pattern: the RTX 5090 delivers 104.8 TFLOPS in both FP32 and FP16 (1:1 ratio), while the Arc B390 delivers 7.680 TFLOPS FP32 and 15.36 TFLOPS FP16 (2:1 ratio).

Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RTX 5090 adds tensor cores for AI workloads, which the Arc B390 does not list. The memory architecture differs completely: the RTX 5090 uses dedicated GDDR7, while the Arc B390 relies on shared system memory.

Specification Differences

The RTX 5090 and Arc B390 differ in nearly every recorded specification field.

Clock speeds: The Arc B390 has a base clock of 300 MHz and boost clock of 2500 MHz. The RTX 5090 has a base clock of 2017 MHz and boost clock of 2407 MHz. The RTX 5090’s memory runs at 1750 MHz (28 Gbps effective), while the Arc B390’s memory speed is system shared.

Memory: The RTX 5090 has 32 GB of GDDR7 on a 512-bit bus with 1.79 TB/s bandwidth. The Arc B390 has no dedicated memory; size, type, and bus width are all system shared, with bandwidth listed as system dependent.

Power: The RTX 5090 has a 575 W TDP, a dual-slot form factor, a 16-pin power connector, and a suggested PSU of 950 W. The Arc B390 has an 80 W TDP, an IGP slot width, no power connectors, and no suggested PSU.

Interface and outputs: The RTX 5090 uses PCIe 5.0 x16 and provides 1x HDMI 2.1b plus 3x DisplayPort 2.1b outputs. The Arc B390 uses an IGP bus interface and lists its display outputs as portable device dependent.

Physical dimensions: The RTX 5090 measures 304 mm in length, 137 mm in height, and 40 mm in width. The Arc B390 has no recorded dimensions.

Release and pricing: The RTX 5090 launched on 2025-01-29 with a launch MSRP of 1,999 USD. The Arc B390 launched on 2026-01-26, with no launch MSRP recorded. The RTX 5090 has predecessors (GeForce 40) and successors (GeForce 60) listed; the Arc B390 has neither.

Benchmark breadth: The RTX 5090 has ten recorded benchmark scores across 3DMark, Geekbench, and Passmark suites. The Arc B390 has a single 3DMark score. The RTX 5090’s average benchmark score is 79,842, versus 1,482 for the Arc B390.