Intel Arc B390 vs NVIDIA GeForce RTX 5090 Mobile Comparison

Head-to-Head Benchmarks

The database contains a single direct comparison between the Intel Arc B390 and the NVIDIA GeForce RTX 5090 Mobile: the 3DMark Steel Nomad DX12 test. In this test, the RTX 5090 Mobile scores 5871, while the Arc B390 records 1482. The delta of -74.8% from the perspective of the Intel part shows that the NVIDIA solution delivers roughly four times the performance in this particular workload. The RTX 5090 Mobile takes the only head-to-head win, and the Arc B390 records zero wins across the available comparison set.

Beyond the single direct test, the broader benchmark database places these two parts in very different performance strata. The Arc B390 sits at the 9th percentile among all GPUs, with an average benchmark score of 1482. Its nearest rivals include the NVIDIA GeForce GT 520MX at 1463 (1.3% behind), the NVIDIA GeForce 800M at 1460 (1.5% behind), the NVIDIA GeForce GT 625 OEM at 1446 (2.5% behind), and the NVIDIA GeForce GT 710 at 1443 (2.7% behind). These are all legacy or entry-level discrete parts, and the Arc B390 edges each by a very narrow margin.

The RTX 5090 Mobile, by contrast, holds the 84th percentile among all GPUs and an average benchmark score of 45152. Its nearest rivals are substantially more powerful parts: the AMD Radeon Pro 5500 XT at 45384 (-0.5% relative to the RTX 5090 Mobile), the NVIDIA GeForce RTX 4070 Ti at 44795 (0.8% ahead), the Intel Arc A730M at 45592 (-1%), and the NVIDIA RTX 5880 Ada Generation at 45972 (-1.8%). The RTX 5090 Mobile effectively trades places with desktop-class GPUs from the previous generation, sitting within a 2% band of all four rivals.

The multi-test record for the RTX 5090 Mobile shows consistent strength across different benchmark families. In Geekbench OpenCL it scores 201834, and in Geekbench Vulkan it scores 198405. The Passmark suite shows a G3D score of 30034, a GPU compute score of 13401, and a G2D score of 1057. Legacy DirectX tests in Passmark record 324 for DirectX 9, 269 for DirectX 11, 183 for DirectX 10, and 138 for DirectX 12. The Arc B390 has only the single Steel Nomad result in the database, so its comparative standing relies entirely on that one measurement.

Where Each One Wins

The functional split is clear from the recorded data. The RTX 5090 Mobile wins every benchmark category in which both parts appear, and it has a much broader test footprint. The 3DMark Steel Nomad DX12 result is the only shared workload, and there the RTX 5090 Mobile is ahead by 74.8%. For any modern DirectX 12 gaming or compute scenario represented by that test, the NVIDIA part dominates.

The Arc B390's nearest-rival data places it in a different competitive context altogether. It competes with GPUs from roughly a decade ago, such as the GeForce GT 710, and it beats them by single-digit percentage points. That suggests the Arc B390 is suited to lightweight or legacy workloads, where its 7.680 TFLOPS FP32 throughput and 120.0 GTexel/s texture rate are sufficient. Its 60.00 GPixel/s pixel rate is roughly one-third of the RTX 5090 Mobile's 169.7 GPixel/s, and its 24 ROPs are far below the NVIDIA part's 112.

The RTX 5090 Mobile's compute capabilities are recorded across multiple APIs. The Geekbench OpenCL score of 201834 and Vulkan score of 198405 indicate strong general-purpose compute performance, while the Passmark GPU compute score of 13401 reinforces that. Its FP32 rating is 31.80 TFLOPS, and its FP16 rating is also 31.80 TFLOPS at a 1:1 ratio, meaning there is no half-rate penalty for FP16 workloads. The Arc B390 offers 15.36 TFLOPS FP16, but at a 2:1 ratio relative to its 7.680 TFLOPS FP32, so FP16 throughput is exactly double FP32.

For users whose workloads align with the recorded Passmark DirectX 9 and DirectX 11 scores, the RTX 5090 Mobile delivers 324 and 269 respectively. The Arc B390 has no corresponding entries in the database, so a direct comparison for older APIs is not possible from the recorded data. The single Steel Nomad result remains the only quantitative link between the two parts.

Architecture Differences

The two GPUs come from entirely different design lineages. The Intel Arc B390 uses the Panther Lake chip with the Xe3-LPG architecture, built on a 3 nm process at Intel's own foundry. It belongs to the Arc Graphics-M (Panther Lake) generation. The NVIDIA GeForce RTX 5090 Mobile uses the GB203 chip with the Blackwell 2.0 architecture, built on a 5 nm process at TSMC. It belongs to the GeForce 50 Mobile generation and succeeds the GeForce 40 Mobile line.

The transistor budgets differ enormously. The RTX 5090 Mobile packs 45,600 million transistors on a 378 mm² die, yielding a transistor density of 120.6M per mm². The Arc B390's transistor count and die size are listed as unknown, so density cannot be computed from the database. The process node advantage goes to Intel at 3 nm versus 5 nm, but the NVIDIA part compensates with a much larger and more complex chip.

Shader resources diverge sharply. The Arc B390 has 1536 shading units, 48 texture mapping units, 24 ROPs, and 12 ray tracing cores. The RTX 5090 Mobile has 10496 shading units, 328 TMUs, 112 ROPs, 82 ray tracing cores, and 328 tensor cores. The Intel part has no tensor core entry in the database, while the NVIDIA part's 328 tensor cores support its AI-oriented workloads. The shading unit count alone is a 6.8x difference in favor of NVIDIA.

Clock behavior also differs. The Arc B390 has a base clock of 300 MHz and a boost clock of 2500 MHz. The RTX 5090 Mobile has a base clock of 990 MHz and a boost clock of 1515 MHz. Despite the lower boost clock, the NVIDIA part's massive shader count delivers far higher throughput. Memory configurations are fundamentally different: the Arc B390 uses system shared memory with a system-dependent bandwidth, while the RTX 5090 Mobile has 24 GB of GDDR7 on a 256-bit bus with 896.0 GB/s of dedicated bandwidth and a memory clock of 1750 MHz (28 Gbps effective).

Power and interface details also separate the parts. The Arc B390 is rated at 80 W TDP, while the RTX 5090 Mobile is rated at 95 W TDP. Both are integrated-class parts with no external power connectors and portable-device-dependent display outputs. The bus interfaces differ: the Arc B390 uses an IGP connection, while the RTX 5090 Mobile uses PCIe 5.0 x16. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RTX 5090 Mobile released on 2025-03-26, while the Arc B390 released on 2026-01-26.

The Verdict

The recorded data supports a decisive separation of roles. The RTX 5090 Mobile is a high-end mobile GPU that competes with desktop-class parts like the RTX 4070 Ti and the RTX 5880 Ada Generation, sitting within 2% of all four of its nearest rivals. Its 84th percentile ranking and average benchmark score of 45152 place it firmly in the upper tier of all recorded GPUs. Its 24 GB GDDR7 memory, 896.0 GB/s bandwidth, and 31.80 TFLOPS FP32 make it suitable for demanding DirectX 12 workloads, compute-heavy applications, and ray-traced content.

The Arc B390 is a low-power integrated GPU whose nearest rivals are legacy parts from the GT 700-series era. Its 9th percentile ranking and average benchmark score of 1482 place it at the entry level of the database. Its 80 W TDP, shared system memory, and 7.680 TFLOPS FP32 indicate a part designed for basic graphics output and light acceleration rather than high-end gaming or professional compute.

The single head-to-head measurement, 3DMark Steel Nomad DX12, shows a 74.8% deficit for the Arc B390 against the RTX 5090 Mobile. That gap is consistent with the percentile difference (9 versus 84) and the average score difference (1482 versus 45152). Users requiring maximum graphics performance in a mobile platform would select the RTX 5090 Mobile based on its recorded benchmark dominance. Users constrained to the Arc B390's performance class should expect results comparable to the GeForce GT 710 or GT 625 OEM, per the nearest-rival deltas of 2.7% and 2.5% respectively.

Neither part has a launch MSRP recorded in the database, so no pricing analysis is possible from the available data. The production status for both is listed as Active.

FAQ

Q: Which GPU wins the only direct benchmark comparison in the database?

A: The NVIDIA GeForce RTX 5090 Mobile wins the 3DMark Steel Nomad DX12 test with a score of 5871, while the Intel Arc B390 scores 1482, a 74.8% difference in favor of NVIDIA.

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

A: The Arc B390's nearest rivals are legacy NVIDIA parts. It is 1.3% ahead of the GeForce GT 520MX, 1.5% ahead of the GeForce 800M, 2.5% ahead of the GeForce GT 625 OEM, and 2.7% ahead of the GeForce GT 710.

Q: What is the RTX 5090 Mobile's competitive position among all GPUs?

A: It sits at the 84th percentile among all GPUs with an average benchmark score of 45152. Its nearest rivals include the AMD Radeon Pro 5500 XT at 45384 (-0.5%), the NVIDIA GeForce RTX 4070 Ti at 44795 (0.8% ahead), the Intel Arc A730M at 45592 (-1%), and the NVIDIA RTX 5880 Ada Generation at 45972 (-1.8%).

Q: What are the memory configurations of these two GPUs?

A: The RTX 5090 Mobile has 24 GB of GDDR7 memory on a 256-bit bus with 896.0 GB/s bandwidth and a 1750 MHz memory clock (28 Gbps effective). The Arc B390 uses system shared memory with system-dependent bandwidth.

Q: How do the compute capabilities differ?

A: The RTX 5090 Mobile delivers 31.80 TFLOPS FP32 and 31.80 TFLOPS FP16 at a 1:1 ratio. The Arc B390 delivers 7.680 TFLOPS FP32 and 15.36 TFLOPS FP16 at a 2:1 ratio.

Q: What are the architecture and process differences?

A: The Arc B390 uses the Panther Lake chip with Xe3-LPG architecture on a 3 nm Intel process. The RTX 5090 Mobile uses the GB203 chip with Blackwell 2.0 architecture on a 5 nm TSMC process with 45,600 million transistors on a 378 mm² die.