Intel Arc Graphics 1 Xe Mobile vs Intel Arc Pro B370 Comparison

# Intel Arc Graphics 1 Xe Mobile vs Intel Arc Pro B370: A Study in Scaling

The database records two Intel integrated graphics parts built on the same Xe3-LPG architecture and 3 nm process, but they occupy very different performance tiers. The Intel Arc Graphics 1 Xe Mobile, based on the Wildcat Lake chip, is a minimal configuration with 128 shading units. The Intel Arc Pro B370, based on the Panther Lake chip, scales that design to 1280 shading units, a tenfold increase in compute resources. Both share the same 25 W TDP, IGP slot width, and system-shared memory, which makes the comparison particularly revealing about what raw silicon scaling can achieve within a fixed power envelope.

Where Each One Wins

The Intel Arc Graphics 1 Xe Mobile wins in exactly one category: it is the smaller, lighter configuration. With 128 shading units, 8 texture mapping units, and 4 render output units, it represents the entry point for Intel's Arc Graphics-M generation. Its boost clock of 2300 MHz is only 100 MHz lower than the Pro B370's 2400 MHz, so the clock speed gap is minor. The real separation comes from the sheer number of execution units. The Arc Graphics 1 Xe Mobile also has a single ray tracing core, which is the minimum viable configuration for hardware-accelerated ray tracing.

The Intel Arc Pro B370 wins in every compute-heavy category that the database tracks. Its 1280 shading units deliver an FP32 throughput of 6.144 TFLOPS, compared to 588.8 GFLOPS for the smaller part. That is a 10.4x advantage in raw floating-point performance. The pixel rate tells a similar story: 48.00 GPixel/s versus 9.200 GPixel/s, a 5.2x gap. Texture rate is 96.00 GTexel/s versus 18.40 GTexel/s, a 5.2x difference. The Pro B370 also has 10 ray tracing cores versus 1, and its 20 ROPs versus 4 ROPs means it can resolve framebuffer operations far more efficiently.

The FP16 numbers reinforce the pattern. The Pro B370 reaches 12.29 TFLOPS with a 2:1 ratio, while the Arc Graphics 1 Xe Mobile manages 1,177.6 GFLOPS. Every measurable throughput metric in the database favors the Pro B370 by a factor of at least 5. The only arena where the smaller part could be considered "winning" is in the context of a system where minimal GPU resources are sufficient, but the recorded data does not contain any benchmark scores to substantiate that. Both parts have zero entries in the head-to-head benchmark array, so the wins are entirely defined by the specification sheets.

The Verdict

The data points to a clear split: the Intel Arc Pro B370 is the part to select when the workload demands parallel compute, high fill rates, or ray tracing. Its 1280 shading units and 10 RT cores put it in a different class from the 128-shader, 1-RT-core Arc Graphics 1 Xe Mobile. For any task that scales with shader count, such as 3D rendering, GPU-accelerated compute, or modern game effects, the Pro B370 delivers roughly ten times the FP32 throughput. The 25 W TDP on both parts means the Pro B370 achieves this without requiring additional power delivery, no external power connectors, and the same IGP slot width.

The Intel Arc Graphics 1 Xe Mobile is the part for scenarios where the GPU is a secondary consideration. Its 588.8 GFLOPS FP32 capacity is sufficient for basic display output, video decode, and light 2D acceleration. The single ray tracing core indicates that hardware RT is present but not intended for serious use. The 4 ROPs limit pixel throughput to 9.200 GPixel/s, which is adequate for modest resolutions but will struggle with high-resolution compositing. The database does not record any benchmark scores for either part, so the verdict rests entirely on the architectural and specification differences.

The release dates place the Arc Pro B370 first, with a recorded release of 2026-01-26, followed by the Arc Graphics 1 Xe Mobile on 2026-04-15. Both are listed as Active production status. The predecessor names differ: HD Graphics-WM for the Pro B370 and HD Graphics-M for the smaller part, which aligns with their respective workstation-mobile and general-mobile positioning. Neither part has a successor recorded.

Head-to-Head Benchmarks

The head-to-head benchmark array in the database is empty, so there are no direct measured scores to compare. However, the specification-derived rates provide a quantitative basis for comparison. The largest win for the Arc Pro B370 is in FP32 compute. At 6.144 TFLOPS, it delivers 10.4 times the 588.8 GFLOPS of the Arc Graphics 1 Xe Mobile. This is the most consequential gap because it directly translates to shader-bound workloads.

The pixel rate comparison shows a 5.2x advantage for the Pro B370: 48.00 GPixel/s versus 9.200 GPixel/s. This gap is driven by the 20 ROPs versus 4 ROPs, despite the boost clock being only 100 MHz higher. Similarly, the texture rate is 96.00 GTexel/s versus 18.40 GTexel/s, again a 5.2x difference, stemming from the 40 TMUs versus 8 TMUs.

The FP16 performance gap mirrors the FP32 gap. The Pro B370 achieves 12.29 TFLOPS, which is 10.4 times the 1,177.6 GFLOPS of the smaller part. This matters for workloads that use reduced precision, such as certain AI inference paths or compute shaders. The ray tracing core count difference is 10 versus 1, which suggests a 10x scaling in RT throughput, though the database does not provide a specific ray tracing benchmark score.

The only metric where the two parts are near parity is the base clock, both at 300 MHz. The boost clocks differ by 100 MHz, which is a 4.3% advantage for the Pro B370. That small clock edge is negligible compared to the execution unit scaling. Both parts share the same memory configuration: System Shared size, type, bus width, and bandwidth. Memory bandwidth is listed as System Dependent, meaning the actual throughput depends on the host platform, not the GPU itself.

FAQ

Q: Which GPU has more shading units?

A: The Intel Arc Pro B370 has 1280 shading units, while the Intel Arc Graphics 1 Xe Mobile has 128. This is a 10x difference in shader count.

Q: What is the FP32 performance difference between the two?

A: The Pro B370 delivers 6.144 TFLOPS, while the Arc Graphics 1 Xe Mobile delivers 588.8 GFLOPS. The Pro B370 is 10.4 times faster in FP32 throughput.

Q: Do both GPUs use the same power envelope?

A: Yes, both are rated at 25 W TDP and use IGP slot width with no power connectors. Neither requires a suggested PSU.

Q: Which GPU has more ray tracing cores?

A: The Intel Arc Pro B370 has 10 ray tracing cores. The Intel Arc Graphics 1 Xe Mobile has 1 ray tracing core.

Q: Are the architectures the same?

A: Both use the Xe3-LPG architecture and are built on a 3 nm process by Intel. The chip names differ: Wildcat Lake for the Arc Graphics 1 Xe Mobile and Panther Lake for the Arc Pro B370.

Q: What is the boost clock difference?

A: The Arc Pro B370 boosts to 2400 MHz, while the Arc Graphics 1 Xe Mobile boosts to 2300 MHz. The base clock is 300 MHz for both.

Architecture Differences

Both GPUs share the Xe3-LPG architecture, which is notable for being Intel's low-power graphics design. The process node is identical at 3 nm, and the foundry is Intel for both. The chip names differ: Wildcat Lake for the Arc Graphics 1 Xe Mobile and Panther Lake for the Arc Pro B370. The generation labels also differ: Arc Graphics-M (Wildcat Lake) versus Arc Graphics-WM (Panther Lake). This indicates a product tiering within the same architectural family.

The shading unit count is the primary architectural differentiator. The Pro B370 uses 1280 shading units, 40 TMUs, and 20 ROPs, which is a configuration that suggests a full or near-full implementation of the Panther Lake GPU block. The Arc Graphics 1 Xe Mobile uses 128 shading units, 8 TMUs, and 4 ROPs, which is exactly one tenth of the Pro B370's count. This is a clean scaling relationship: 1280/128 = 10, 40/8 = 5, 20/4 = 5. The TMU and ROP counts scale by 5, not 10, which means the Pro B370 has proportionally more shaders per texture unit and per ROP.

The ray tracing core count also scales by 10: 10 versus 1. This suggests that each RT core is paired with 128 shading units in both designs. The boost clock advantage of the Pro B370 (2400 MHz versus 2300 MHz) is modest, indicating that the architecture is not clock-limited at this power level. The FP16 to FP32 ratio is 2:1 for both, which is consistent with the same ALU design.

The API support is identical: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. This means software compatibility is not a differentiator. The display outputs are also the same: Portable Device Dependent, which is expected for integrated parts.

Specification Differences

The specification table shows clear differences in every compute resource field. The shading units are 1280 for the Pro B370 versus 128 for the Arc Graphics 1 Xe Mobile. The TMUs are 40 versus 8, and the ROPs are 20 versus 4. The RT cores are 10 versus 1. The pixel rate is 48.00 GPixel/s versus 9.200 GPixel/s. The texture rate is 96.00 GTexel/s versus 18.40 GTexel/s. The FP32 throughput is 6.144 TFLOPS versus 588.8 GFLOPS. The FP16 throughput is 12.29 TFLOPS versus 1,177.6 GFLOPS.

The boost clock differs by 100 MHz: 2400 MHz for the Pro B370 and 2300 MHz for the Arc Graphics 1 Xe Mobile. The base clock is identical at 300 MHz. The chip name differs (Panther Lake versus Wildcat Lake), as does the generation label (Arc Graphics-WM versus Arc Graphics-M). The release dates differ, with the Pro B370 on 2026-01-26 and the Arc Graphics 1 Xe Mobile on 2026-04-15.

The fields that are identical include the process node (3 nm), foundry (Intel), TDP (25 W), slot width (IGP), power connectors (None), bus interface (IGP), display outputs (Portable Device Dependent), and all API support levels. The memory configuration is also identical: System Shared for size, type, and bus width, with System Dependent bandwidth. Neither part has a launch MSRP recorded, and both have a percentile rank of 50 against all GPUs. The predecessor names differ: HD Graphics-WM for the Pro B370 and HD Graphics-M for the Arc Graphics 1 Xe Mobile. Both have no successor recorded.