Intel Arc B390 vs NVIDIA GeForce RTX 5080 Mobile Comparison

Intel Arc B390 and NVIDIA GeForce RTX 5080 Mobile occupy very different positions in the database's benchmark hierarchy. The RTX 5080 Mobile sits in the 81st percentile of all GPUs, while the Arc B390 lands in the 9th percentile. A single shared benchmark, 3DMark Steel Nomad DX12, provides the direct comparison: the NVIDIA part scores 4952 against 1482 for the Intel part, a 70.1% deficit. The data indicates that these are not competing products in any practical sense, but the comparison still reveals distinct architectural and performance characteristics worth examining.

Where Each One Wins

The NVIDIA GeForce RTX 5080 Mobile wins the only head-to-head benchmark recorded in the database. Across its broader benchmark suite, it shows consistent strength in compute-heavy workloads. Its Geekbench OpenCL score of 166986 and Vulkan score of 169754 indicate robust general-purpose compute performance. PassMark results reinforce this: a G3D score of 27711, a GPU Compute score of 12134, and a G2D score of 1095. Even its legacy DirectX scores, ranging from 116 in DirectX 12 to 314 in DirectX 9, show functional capability across API generations. The RTX 5080 Mobile also delivers a texture rate of 360.0 GTexel/s and a pixel rate of 144.0 GPixel/s, figures that place it firmly in the high-performance mobile segment.

The Intel Arc B390, by contrast, has only one recorded benchmark score: 1482 in 3DMark Steel Nomad DX12. Its nearest rivals in the database are NVIDIA GeForce GT 520MX at 1463, GeForce 800M at 1460, GT 625 OEM at 1446, and GT 710 at 1443. The Arc B390 leads those parts by margins of 1.3%, 1.5%, 2.5%, and 2.7%, respectively. These deltas are small, indicating that the Arc B390 clusters with entry-level discrete GPUs from past generations. Its wins are narrow and incremental, not categorical. The Arc B390 does offer a 3 nm process node and the Xe3-LPG architecture, but the benchmark data shows that its actual measured performance aligns with older, low-end parts.

In terms of raw compute throughput, the RTX 5080 Mobile delivers 23.04 TFLOPS FP32 and 23.04 TFLOPS FP16 (1:1), while the Arc B390 delivers 7.680 TFLOPS FP32 and 15.36 TFLOPS FP16 (2:1). The NVIDIA part also has a 16 GB GDDR7 memory subsystem with a 256-bit bus and 896.0 GB/s bandwidth, versus the Arc B390's system-shared memory with system-dependent bandwidth. The RTX 5080 Mobile's shading unit count of 7680, TMUs of 240, and ROPs of 96 dwarf the Arc B390's 1536 shading units, 48 TMUs, and 24 ROPs. Every measurable specification favors the NVIDIA part except for process node, where the Intel chip uses 3 nm versus 5 nm for the NVIDIA chip.

The Verdict

The database shows a clear performance hierarchy. The NVIDIA GeForce RTX 5080 Mobile is the superior GPU by a wide margin. Its 3DMark Steel Nomad score is 3.34 times higher than the Intel Arc B390's score. The RTX 5080 Mobile's nearest rivals include the NVIDIA GeForce RTX 4080 Mobile, which it edges by 0.6%, and the NVIDIA GeForce MX570, which it leads by only 0.1%. The Arc B390, meanwhile, trades positions with decade-old parts like the GT 520MX and GT 710.

For users seeking any level of modern gaming or compute performance, the RTX 5080 Mobile is the only viable choice from this comparison. Its 81st percentile ranking places it above the vast majority of all GPUs in the database. The Arc B390's 9th percentile ranking places it below nearly all of them. The data does not support any scenario where the Arc B390 outperforms the RTX 5080 Mobile in a shared workload. The RTX 5080 Mobile also shows superiority in every recorded benchmark it appears in, including legacy DirectX tests where it still posts scores well above the Arc B390's single result.

The Arc B390 may hold interest as an integrated graphics solution with a modern architecture, but its measured performance is not competitive with the RTX 5080 Mobile. Users who require the RTX 5080 Mobile's feature set, including 60 ray tracing cores and 240 tensor cores, will find those capabilities entirely absent from the Arc B390's specification sheet, which lists 12 ray tracing cores and no tensor cores. The verdict from the data is unambiguous: the RTX 5080 Mobile wins every measured comparison.

Head-to-Head Benchmarks

The only direct benchmark shared between the two GPUs is 3DMark Steel Nomad DX12. The NVIDIA GeForce RTX 5080 Mobile scores 4952, while the Intel Arc B390 scores 1482. The delta is 70.1% in favor of the NVIDIA part. This single result encapsulates the entire performance gap. The RTX 5080 Mobile's score is more than triple the Arc B390's, a margin that no other benchmark in the database contradicts.

The RTX 5080 Mobile's other benchmark results provide additional context. Its Geekbench Vulkan score of 169754 and OpenCL score of 166986 are both extremely high, reflecting strong driver optimization and hardware throughput. Its PassMark G3D score of 27711 is nearly double its GPU Compute score of 12134, indicating that the part is particularly strong in graphics rendering tasks. The Arc B390 has no comparable results in the database, so the comparison remains limited to the Steel Nomad test.

Architectural specifications reinforce the benchmark outcome. The RTX 5080 Mobile has a boost clock of 1500 MHz, a base clock of 975 MHz, and memory clock of 1750 MHz (28 Gbps effective). The Arc B390 has a boost clock of 2500 MHz and a base clock of 300 MHz, but its memory is system-shared and its bandwidth is system-dependent. Despite the Arc B390's higher boost clock, its lower shader count and memory bandwidth result in far lower throughput. The RTX 5080 Mobile's texture rate of 360.0 GTexel/s and pixel rate of 144.0 GPixel/s are 3 times and 2.4 times higher than the Arc B390's respective rates of 120.0 GTexel/s and 60.00 GPixel/s.

FAQ

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

A: The NVIDIA GeForce RTX 5080 Mobile scores 4952, while the Intel Arc B390 scores 1482. The RTX 5080 Mobile leads by 70.1%.

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

A: The Arc B390 leads the NVIDIA GeForce GT 520MX by 1.3%, the GeForce 800M by 1.5%, the GT 625 OEM by 2.5%, and the GT 710 by 2.7%. All deltas are small, indicating close performance parity.

Q: What are the memory specifications of each GPU?

A: The RTX 5080 Mobile has 16 GB of GDDR7 memory on a 256-bit bus with 896.0 GB/s bandwidth. The Arc B390 uses system-shared memory with system-dependent bandwidth and type.

Q: Which GPU has more shading units?

A: The RTX 5080 Mobile has 7680 shading units, while the Arc B390 has 1536. The RTX 5080 Mobile also has 240 TMUs and 96 ROPs versus 48 TMUs and 24 ROPs on the Arc B390.

Q: What process nodes do the two GPUs use?

A: The Intel Arc B390 uses a 3 nm process node, fabricated by Intel. The NVIDIA GeForce RTX 5080 Mobile uses a 5 nm process node, fabricated by TSMC.

Q: Which GPU has ray tracing and tensor cores?

A: Both have ray tracing cores: 12 on the Arc B390 and 60 on the RTX 5080 Mobile. Only the RTX 5080 Mobile has tensor cores, with 240 of them. The Arc B390 lists no tensor cores.

Architecture Differences

The Intel Arc B390 is built on the Xe3-LPG architecture, part of the Panther Lake chip, and belongs to the Arc Graphics-M (Panther Lake) generation. It uses a 3 nm process node from Intel's own foundry. The GPU is an integrated graphics processor (IGP) with a slot width of IGP and no power connectors. Its bus interface is also IGP, meaning it relies on system memory rather than dedicated VRAM. The architecture supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Its FP32 throughput is 7.680 TFLOPS, and its FP16 throughput is 15.36 TFLOPS with a 2:1 ratio. The chip has 1536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores. It uses a base clock of 300 MHz and a boost clock of 2500 MHz. Its production status is Active, and its release date is recorded as 2026-01-26.

The NVIDIA GeForce RTX 5080 Mobile is built on the Blackwell 2.0 architecture, using the GB203 chip, and belongs to the GeForce 50 Mobile generation. It uses a 5 nm process node from TSMC. The chip contains 45,600 million transistors on a 378 mm² die, yielding a transistor density of 120.6M per mm². The GPU is also an IGP in terms of slot width, with no power connectors, but it uses a PCIe 5.0 x16 bus interface. Its memory is dedicated: 16 GB of GDDR7 on a 256-bit bus with 896.0 GB/s bandwidth. The base clock is 975 MHz, the boost clock is 1500 MHz, and the memory clock is 1750 MHz (28 Gbps effective). It has 7680 shading units, 240 TMUs, 96 ROPs, 60 ray tracing cores, and 240 tensor cores. Its FP32 throughput is 23.04 TFLOPS, and its FP16 throughput is 23.04 TFLOPS with a 1:1 ratio. It supports the same API set as the Arc B390: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Its production status is Active, and its release date is recorded as 2025-04-01. It lists the GeForce 40 Mobile as its predecessor.

The architectural differences are substantial. The Arc B390 has a smaller process node but vastly fewer execution resources. The RTX 5080 Mobile has more than 5 times the shading units, 5 times the TMUs, 4 times the ROPs, and 5 times the ray tracing cores. The tensor core count difference is absolute: 240 versus none. Memory architecture also diverges completely, with the RTX 5080 Mobile using dedicated GDDR7 and the Arc B390 sharing system memory. Clock speeds favor the Intel part in boost frequency, 2500 MHz versus 1500 MHz, but this does not compensate for the resource imbalance. The RTX 5080 Mobile's predecessor is listed, while the Arc B390 has no predecessor or successor in the database. Both GPUs are active in production, but their target segments, based on the recorded data, are clearly different.