Intel Arc Pro B390 vs NVIDIA GeForce RTX 5080 Comparison

FAQ

Q: What are the two products compared in this analysis?

A: The Intel Arc Pro B390, an integrated graphics processor based on the Xe3-LPG architecture, and the NVIDIA GeForce RTX 5080, a discrete add-in card based on the Blackwell 2.0 architecture.

Q: How do their benchmark scores compare overall?

A: The NVIDIA GeForce RTX 5080 has an average benchmark score of 56083, placing it in the 87th percentile of all GPUs. The Intel Arc Pro B390 has a percentile ranking of 50, with its average benchmark score recorded as 0 in the database.

Q: What is the process node and foundry for each chip?

A: The Intel Arc Pro B390 uses a 3 nm process manufactured by Intel, while the NVIDIA GeForce RTX 5080 uses a 5 nm process manufactured by TSMC.

Q: What are the memory configurations of the two products?

A: The Intel Arc Pro B390 uses System Shared memory, with bandwidth described as System Dependent. The NVIDIA GeForce RTX 5080 has 16 GB of GDDR7 memory on a 256-bit bus, providing 960.0 GB/s of bandwidth.

Q: What are the power consumption figures?

A: The Intel Arc Pro B390 has a TDP of 80 W and requires no power connectors. The NVIDIA GeForce RTX 5080 has a TDP of 360 W and uses a single 16-pin power connector.

Q: Which product has a higher shading unit count?

A: The NVIDIA GeForce RTX 5080 has 10752 shading units, compared to 1536 shading units on the Intel Arc Pro B390.

Where Each One Wins

The database indicates a complete separation in use-case applicability. The Intel Arc Pro B390 is an integrated graphics processor, meaning it is built into the host processor and is intended for systems where a discrete GPU is not present. Its performance class, reflected by its 50th percentile ranking, positions it for basic graphics output, media playback, and light compute workloads. The system-shared memory architecture means its performance is directly tied to the host system's memory configuration, making it suitable for portable devices where space and power are at a premium.

The NVIDIA GeForce RTX 5080, with its 87th percentile ranking and average benchmark score of 56083, is designed for high-end gaming, professional rendering, and compute-intensive tasks. Its dedicated 16 GB GDDR7 memory pool and 960.0 GB/s bandwidth allow it to handle large datasets and high-resolution textures without contending with the host CPU for memory access. The 360 W TDP and requirement for a dedicated power connector indicate a desktop-oriented design where maximum performance is the primary objective.

The recorded data shows that the RTX 5080 wins in every benchmark category where scores exist. The Intel Arc Pro B390 has no recorded benchmark scores in the database, meaning its wins cannot be quantified in direct comparison. Instead, its advantage lies in its integration: it consumes 80 W versus 360 W, occupies no expansion slot, and requires no separate memory allocation. This makes it the appropriate choice for thin-and-light systems where the RTX 5080's 304 mm length and dual-slot footprint are impossible to accommodate.

Architecture Differences

The two products represent fundamentally different design philosophies. The Intel Arc Pro B390 uses the Xe3-LPG architecture, built on Intel's 3 nm process. It is part of the Arc Graphics-WM generation, specifically designed for Panther Lake processors. The chip includes 1536 shading units, 48 texture mapping units, 24 raster operation units, and 12 ray tracing cores. Its FP32 compute throughput is 7.680 TFLOPS, and FP16 throughput is 15.36 TFLOPS using a 2:1 ratio. The architecture supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

The NVIDIA GeForce RTX 5080 uses the Blackwell 2.0 architecture, built on TSMC's 5 nm process. The GB203 chip contains 45,600 million transistors on a 378 mm² die, yielding a transistor density of 120.6M per mm². It has 10752 shading units, 336 texture mapping units, 112 raster operation units, 84 ray tracing cores, and 336 tensor cores. Its FP32 throughput is 56.28 TFLOPS, and FP16 throughput is also 56.28 TFLOPS, operating at a 1:1 ratio. It supports the same DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4 APIs.

The RTX 5080's tensor cores are a key differentiator, providing dedicated hardware for AI acceleration, including DLSS and other neural network workloads. The Intel Arc Pro B390 has no tensor cores listed. The RTX 5080 also has a much larger memory subsystem: 16 GB of GDDR7 on a 256-bit bus versus system-shared memory on the Intel part. The transistor count difference is substantial, with NVIDIA's chip containing 45,600 million transistors compared to Intel's unknown count, reflecting the scale of the compute resources allocated to each design.

Specification Differences

The specification tables show stark contrasts across nearly every measurable field. The process node differs: 3 nm for Intel versus 5 nm for NVIDIA. The foundry also differs: Intel uses its own fabs, while NVIDIA uses TSMC. The clock speeds tell a similar story. The Intel Arc Pro B390 has a base clock of 300 MHz and a boost clock of 2500 MHz. The RTX 5080 has a base clock of 2295 MHz and a boost clock of 2617 MHz, with memory clocked at 1875 MHz (30 Gbps effective).

The memory configuration is fundamentally different. The Intel part uses System Shared memory, with no dedicated size, type, bus width, or bandwidth figures. The NVIDIA part uses 16 GB of GDDR7 on a 256-bit bus with 960.0 GB/s bandwidth. The compute unit counts are heavily skewed toward NVIDIA: 10752 shading units versus 1536, 336 TMUs versus 48, 112 ROPs versus 24, 84 RT cores versus 12, and 336 tensor cores versus none.

The pixel rate for the RTX 5080 is 293.1 GPixel/s versus 60.00 GPixel/s for the Intel part. Texture rate is 879.3 GTexel/s versus 120.0 GTexel/s. FP32 performance is 56.28 TFLOPS versus 7.680 TFLOPS. Power consumption is 360 W versus 80 W. The physical form factors are entirely different: the Intel part is an IGP with no slot width, while the NVIDIA part is a dual-slot card measuring 304 mm in length, 137 mm in height, and 40 mm in width. The bus interface differs: IGP versus PCIe 5.0 x16.

The RTX 5080 has a launch MSRP of 999 USD. The Intel Arc Pro B390 has no recorded launch MSRP. The RTX 5080 was released on 2025-01-29, while the Intel part was released on 2026-01-26.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark results between these two products. The wins counter shows 0 for both sides. However, the RTX 5080 has a full suite of individual benchmark scores, while the Intel Arc Pro B390 has none recorded.

The RTX 5080's scores across various tests illustrate its performance profile. In 3DMark Steel Nomad DX12, it scores 8637. In Geekbench OpenCL, it scores 235901. In Geekbench Vulkan, it scores 255450. PassMark results include: DirectX 10 at 208, DirectX 11 at 324, DirectX 12 at 151, DirectX 9 at 389, G2D at 1415, G3D at 36565, and GPU Compute at 21789. These scores contribute to its average benchmark score of 56083.

The nearest rivals to the RTX 5080, based on average score, are all AMD products. The AMD Radeon 8060S has an average score of 55757, which is 0.6% lower than the RTX 5080. The AMD Radeon RX 6750 GRE 12 GB scores 55698, 0.7% lower. The AMD Radeon Pro W5700X scores 54828, 2.3% lower. The AMD Radeon RX 9070 GRE scores 57367, which is 2.2% higher than the RTX 5080.

The RTX 5080's percentile ranking of 87 places it well above the median GPU, and its average score of 56083 is roughly six times higher than what a 50th-percentile GPU would typically achieve. The Intel Arc Pro B390's 50th-percentile ranking indicates it sits at the middle of the performance distribution, but the absence of benchmark scores means the database cannot quantify its exact position relative to the RTX 5080.

The data confirms that the RTX 5080 is the only product of the two with measurable performance records. Its compute-heavy architecture, large memory pool, and high power envelope position it as a dedicated performance part. The Intel Arc Pro B390, with its system-shared memory and low power draw, serves an entirely different market segment where integration and efficiency take precedence over raw throughput.