Intel Arc Graphics 1 Xe Mobile vs Intel Arc Pro B390 Comparison

Where Each One Wins

The Intel Arc Graphics 1 Xe Mobile and Intel Arc Pro B390 occupy different tiers within the same Xe3-LPG architecture family, and the data confirms a clear performance hierarchy. The Arc Pro B390 wins every category where raw compute throughput matters: shading, texturing, pixel output, ray tracing, and FP32/FP16 processing. The Arc Graphics 1 Xe Mobile, by contrast, wins only in efficiency-oriented contexts, primarily because its power envelope is dramatically lower.

The use-case split is straightforward. The Arc Graphics 1 Xe Mobile, with a 25 W TDP and 128 shading units, is positioned for lightweight portable devices where sustained battery life and modest graphical demands take priority. Its 588.8 GFLOPS FP32 throughput and 9.200 GPixel/s pixel rate are sufficient for basic 2D acceleration, video playback, and undemanding 3D workloads. The Arc Pro B390, with an 80 W TDP and 1536 shading units, delivers 7.680 TFLOPS FP32, which is exactly 13 times higher. This places it in a different class entirely, suited for professional graphics work, content creation, and heavier compute tasks.

The recorded data shows zero head-to-head benchmark entries and zero wins for either part, so the analysis rests on the architectural specifications. The percentile ranking for both is 50.0 relative to all GPUs, which is a neutral midpoint, but this does not reflect the massive internal gap in raw resources. The Arc Pro B390 has 12 times the shading units, 6 times the texture mapping units, 6 times the ROPs, and 12 times the ray tracing cores. Those ratios translate directly into workload advantages.

For texturing, the B390 delivers 120.0 GTexel/s versus 18.40 GTexel/s for the mobile part, a 6.5x advantage. For pixel fill, the B390 outputs 60.00 GPixel/s versus 9.200 GPixel/s, a 6.5x margin. These are not incremental differences; they represent fundamentally different performance classes. The Arc Graphics 1 Xe Mobile wins only in power efficiency, where its 25 W envelope allows deployment in fanless or passively cooled ultraportables, while the B390's 80 W requirement demands more robust thermal solutions.

Architecture Differences

Both parts share the Xe3-LPG architecture and use Intel's 3 nm process node, fabricated at Intel's own foundry. The underlying design philosophy is identical, but the resource allocation diverges sharply. The Arc Graphics 1 Xe Mobile is built on the Wildcat Lake chip, while the Arc Pro B390 uses the Panther Lake chip. This chip difference accounts for the dramatic scaling in execution resources.

The mobile part carries 128 shading units, 8 TMUs, and 4 ROPs, with a single ray tracing core. The Pro B390 scales this to 1536 shading units, 48 TMUs, and 24 ROPs, with 12 ray tracing cores. The ray tracing core count is particularly telling: 12 versus 1. This indicates the B390 is designed to handle hardware-accelerated ray tracing workloads, whereas the mobile part's single RT core is more of a token implementation, useful for basic effects but not for sustained ray tracing performance.

Clock behavior also differs. Both parts have a 300 MHz base clock, but the boost clock rises to 2300 MHz on the mobile part and 2500 MHz on the Pro B390. That 200 MHz boost advantage, combined with 12 times the execution resources, explains why the FP32 throughput gap is so large. The FP16 figures follow the same 2:1 ratio pattern: 1,177.6 GFLOPS for the mobile part and 15.36 TFLOPS for the B390.

Memory architecture is identical in configuration: both use system shared memory with a system dependent bus width and bandwidth. Neither has dedicated VRAM, which means performance scales with the host system's memory subsystem. This is a common trait for integrated graphics parts, and both are classified as IGP with no power connectors and portable device dependent display outputs.

The API support is identical: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. This means software compatibility is the same across both, and the difference lies purely in execution capability, not feature support. The production status for both is Active, and both have predecessors in the HD Graphics line, with the mobile part succeeding HD Graphics-M and the Pro part succeeding HD Graphics-WM.

Head-to-Head Benchmarks

The database contains no recorded head-to-head benchmark results for these two parts, and the wins counter shows 0 for each. This absence of direct measurement data means the comparison must rely on the specification-derived throughput figures, which are part of the recorded data.

The most striking single number is the FP32 throughput difference. The Arc Pro B390 delivers 7.680 TFLOPS, which is exactly 13 times the 588.8 GFLOPS of the Arc Graphics 1 Xe Mobile. This ratio is consistent with the 12x shading unit count, slightly amplified by the higher boost clock. For any FP32-heavy workload, such as scientific computing, physics simulation, or general GPU compute, the B390 is in a completely different league.

Pixel fill rate shows a 6.5x gap: 60.00 GPixel/s versus 9.200 GPixel/s. This affects rasterization-heavy workloads, including traditional 3D rendering and high-resolution display output. The texture fill rate gap is also 6.5x: 120.0 GTexel/s versus 18.40 GTexel/s. Texturing is critical for game rendering and image processing, and the B390's advantage here is substantial.

The ray tracing core count difference, 12 versus 1, suggests that the B390 can maintain meaningful ray tracing performance, while the mobile part would struggle with anything beyond basic ray traced effects. The 2.5 GHz boost clock on the B390, versus 2.3 GHz on the mobile part, provides a 8.7% clock advantage on top of the massive resource advantage.

The FP16 throughput figures follow the same pattern: 15.36 TFLOPS versus 1,177.6 GFLOPS, a 13x gap. For machine learning inference and other FP16 workloads, the B390 is the clear choice. The mobile part's FP16 capability is present but limited to light workloads.

Specification Differences

The two parts differ in several key fields, while sharing others. The following fields are where the two diverge:

• Chip: Wildcat Lake versus Panther Lake
• Generation: Arc Graphics-M (Wildcat Lake) versus Arc Graphics-WM (Panther Lake)
• Boost Clock: 2300 MHz versus 2500 MHz
• Shading Units: 128 versus 1536
• TMUs: 8 versus 48
• ROPs: 4 versus 24
• RT Cores: 1 versus 12
• Pixel Rate: 9.200 GPixel/s versus 60.00 GPixel/s
• Texture Rate: 18.40 GTexel/s versus 120.0 GTexel/s
• FP32: 588.8 GFLOPS versus 7.680 TFLOPS
• FP16: 1,177.6 GFLOPS versus 15.36 TFLOPS
• TDP: 25 W versus 80 W
• Release Date: 2026-04-15 versus 2026-01-26
• Predecessor: HD Graphics-M versus HD Graphics-WM

The fields that are identical include the architecture (Xe3-LPG), process node (3 nm), foundry (Intel), base clock (300 MHz), memory configuration (system shared, system dependent bandwidth), API support (DirectX 12 Ultimate, OpenGL 4.6, Vulkan 1.4), slot width (IGP), power connectors (None), bus interface (IGP), display outputs (portable device dependent), and production status (Active). Neither part has a launch MSRP recorded in the database.

FAQ

Q: Which part has more shading units?

A: The Intel Arc Pro B390 has 1536 shading units, which is 12 times the 128 shading units found in the Intel Arc Graphics 1 Xe Mobile.

Q: What is the FP32 performance difference?

A: The Arc Pro B390 delivers 7.680 TFLOPS FP32, while the Arc Graphics 1 Xe Mobile delivers 588.8 GFLOPS. This is a 13x advantage for the B390.

Q: Do both parts use the same memory type?

A: Yes, both use system shared memory with a system dependent bus width and bandwidth. Neither has dedicated VRAM.

Q: How do the ray tracing capabilities compare?

A: The Arc Pro B390 has 12 ray tracing cores, while the Arc Graphics 1 Xe Mobile has only 1. The B390 is substantially more capable for ray traced workloads.

Q: What is the TDP of each part?

A: The Arc Graphics 1 Xe Mobile has a 25 W TDP, and the Arc Pro B390 has an 80 W TDP.

Q: Do both parts support the same graphics APIs?

A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: Which part was released earlier?

A: The Intel Arc Pro B390 was released on 2026-01-26, while the Intel Arc Graphics 1 Xe Mobile was released on 2026-04-15.

The Verdict

The data clearly separates these two parts into distinct usage categories. The Intel Arc Pro B390 is the superior performer across every computational metric recorded: FP32, FP16, pixel rate, texture rate, and ray tracing core count. Its 7.680 TFLOPS FP32 output and 60.00 GPixel/s pixel rate make it suitable for professional graphics work, content creation, and any workload that demands sustained compute throughput. The 12 ray tracing cores provide meaningful hardware acceleration for ray traced rendering, and the 80 W TDP indicates a part designed for devices with adequate cooling.

The Intel Arc Graphics 1 Xe Mobile, with its 25 W TDP and 588.8 GFLOPS FP32, is positioned for ultraportable devices where power consumption is the primary constraint. Its 128 shading units and single ray tracing core are sufficient for basic graphical output, video playback, and light 3D acceleration, but not for demanding workloads. The 2300 MHz boost clock and 9.200 GPixel/s pixel rate are adequate for standard display tasks.

Users who need compute performance should select the Arc Pro B390, as its 13x FP32 advantage and 6.5x texture and pixel rate advantages provide headroom for professional applications. Users who prioritize power efficiency and operate within a 25 W envelope should select the Arc Graphics 1 Xe Mobile, as its lower TDP enables deployment in thinner, lighter devices. The choice is not about which part is better in absolute terms, but which matches the power and performance requirements of the target system. Both parts share the same architecture, process node, and API support, so software compatibility is identical; the difference is purely in execution resources and power budget.