Intel Arc Graphics 2 Xe Mobile vs Intel Arc Pro B370 Comparison

Where Each One Wins

The recorded data places both parts in the same performance percentile band, with each sitting at the 50th percentile among all GPUs in the database. That parity in percentile, however, masks a clear split in intended workloads. The Intel Arc Graphics 2 Xe Mobile is configured for efficiency and lightweight graphics duty. Its 256 shading units, 16 texture mapping units, and 8 raster operation units define a part aimed at modest resolutions and less demanding titles. The Intel Arc Pro B370, by contrast, carries 1280 shading units, 40 TMUs, and 20 ROPs, and its compute rates are multiples of the smaller part. The data shows a part that is built to handle heavier geometry, higher pixel fill, and more parallel shading work.

The Arc Graphics 2 Xe Mobile posts a pixel rate of 20.00 GPixel/s and a texture rate of 40.00 GTexel/s. Those figures point to a chip that can sustain decent output on small displays or with reduced settings. Its boost clock of 2500 MHz is actually 100 MHz higher than the Pro B370's 2400 MHz boost, which suggests the smaller part can keep up in lightly threaded or latency-sensitive scenarios where raw shader count matters less. The Arc Pro B370 counters with a pixel rate of 48.00 GPixel/s and a texture rate of 96.00 GTexel/s. In any fill-rate bound scene, the Pro part should pull ahead decisively.

For FP32 compute, the Arc Pro B370 delivers 6.144 TFLOPS versus 1,280.0 GFLOPS for the Arc Graphics 2 Xe Mobile. That is a 4.8x advantage in raw shader throughput. FP16 numbers follow the same pattern: 12.29 TFLOPS for the Pro part against 2.560 TFLOPS for the mobile part. The use-case split is therefore straightforward. The Arc Graphics 2 Xe Mobile wins where power envelope and system integration matter, while the Arc Pro B370 wins where shader throughput, ray tracing, and fill rate are the priority.

FAQ

Q: Which GPU has the higher boost clock?

A: The Intel Arc Graphics 2 Xe Mobile boosts to 2500 MHz, while the Intel Arc Pro B370 boosts to 2400 MHz. The mobile part holds a 100 MHz advantage.

Q: How do the two compare in shading units?

A: The Intel Arc Pro B370 has 1280 shading units, which is five times the 256 shading units found in the Intel Arc Graphics 2 Xe Mobile.

Q: Do both GPUs support the same graphics APIs?

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

Q: Are both parts built on the same process node?

A: Yes. Both the Intel Arc Graphics 2 Xe Mobile and the Intel Arc Pro B370 use a 3 nm process from Intel.

Q: What is the memory configuration for each GPU?

A: Both use System Shared memory, with the same System Shared bus width and memory type. Bandwidth is listed as System Dependent for both.

Q: Do these GPUs have dedicated power connectors?

A: No. Both are IGP parts with no power connectors, and both carry a 25 W TDP.

Head-to-Head Benchmarks

The benchmark database contains no direct head-to-head runs for these two parts, so the comparison rests on the computed specification rates recorded in the database. The most lopsided gap is in FP32 throughput. The Arc Pro B370 posts 6.144 TFLOPS, which is 4.8 times the 1,280.0 GFLOPS of the Arc Graphics 2 Xe Mobile. In practical terms, any shader-heavy workload will finish far sooner on the Pro part. The FP16 comparison is nearly identical in ratio: 12.29 TFLOPS against 2.560 TFLOPS, a difference of roughly 4.8x as well.

Texture rate tells a similar story. The Arc Pro B370 reaches 96.00 GTexel/s, while the Arc Graphics 2 Xe Mobile manages 40.00 GTexel/s. The Pro part is 2.4x faster at texture filtering. Pixel rate shows the Pro part at 48.00 GPixel/s versus 20.00 GPixel/s for the mobile part, a 2.4x gap. These fill-rate differences will show up in games or applications that push high resolutions or complex material blending.

Ray tracing resources also favor the Pro part heavily. The Arc Pro B370 has 10 ray tracing cores, while the Arc Graphics 2 Xe Mobile has only 2. That is a 5x difference in RT core count, which should translate to noticeably better ray-traced effects in supported titles, assuming other bottlenecks are managed.

The one specification where the smaller part leads is clock speed. The Arc Graphics 2 Xe Mobile has a 2500 MHz boost versus 2400 MHz for the Arc Pro B370. The 100 MHz advantage is small and unlikely to offset the Pro part's massive resource advantage in throughput-bound workloads. The base clocks are identical at 300 MHz.

Both parts share the same TDP of 25 W. That is notable because the Arc Pro B370 delivers far higher throughput within the same power envelope, which makes the larger part the more efficient choice per unit of work. The mobile part's higher boost clock does not compensate for the 5x shading unit deficit when both are running under the same power limit.

Specification Differences

The database lists several fields where the two parts diverge. Shading units: the Arc Pro B370 has 1280, the Arc Graphics 2 Xe Mobile has 256. Texture mapping units: 40 for the Pro part, 16 for the mobile part. Raster operation units: 20 versus 8. Ray tracing cores: 10 versus 2. Boost clock: 2400 MHz for the Pro part, 2500 MHz for the mobile part. Pixel rate: 48.00 GPixel/s versus 20.00 GPixel/s. Texture rate: 96.00 GTexel/s versus 40.00 GTexel/s. FP32 compute: 6.144 TFLOPS versus 1,280.0 GFLOPS. FP16 compute: 12.29 TFLOPS versus 2.560 TFLOPS.

The chip names also differ. The Arc Graphics 2 Xe Mobile uses the Wildcat Lake chip, while the Arc Pro B370 uses the Panther Lake chip. The generation strings differ as well: Arc Graphics-M (Wildcat Lake) versus Arc Graphics-WM (Panther Lake). Predecessors are listed as HD Graphics-M for the mobile part and HD Graphics-WM for the Pro part. Release dates differ: the Arc Pro B370 entered the database with a 2026-01-26 release, and the Arc Graphics 2 Xe Mobile followed with a 2026-04-15 release.

Fields that are identical include the 3 nm process node, Intel as the foundry, the Xe3-LPG architecture, base clock of 300 MHz, memory type and size (System Shared), bus width (System Shared), bandwidth (System Dependent), TDP of 25 W, slot width of IGP, no power connectors, IGP bus interface, Portable Device Dependent display outputs, DirectX 12 Ultimate (12_2), OpenGL 4.6, Vulkan 1.4, and Active production status. Neither part lists a launch MSRP in the database.

Architecture Differences

Both GPUs share the Xe3-LPG architecture, which is Intel's low-power graphics design. The key architectural difference lies in execution resources rather than ISA or feature set. The Arc Pro B370 scales the Xe3-LPG design to 1280 shading units, 40 TMUs, 20 ROPs, and 10 ray tracing cores. The Arc Graphics 2 Xe Mobile uses a much smaller configuration: 256 shading units, 16 TMUs, 8 ROPs, and 2 ray tracing cores. The architecture is the same, but the width of the execution pipelines is dramatically different.

The process node is identical at 3 nm, and Intel is the foundry for both. The transistor count and die size are listed as unknown for both, so no density comparison is possible from the recorded data. The chip names point to different families within Intel's lineup: Wildcat Lake for the mobile part and Panther Lake for the Pro part. The generation labels in the database reflect that split, with the mobile part belonging to Arc Graphics-M (Wildcat Lake) and the Pro part to Arc Graphics-WM (Panther Lake).

Cache details are not recorded in the database for either part. Tensor cores are listed as null for both, meaning the database does not attribute dedicated AI acceleration hardware to either GPU. The 2:1 FP16 ratio on both parts indicates that FP16 throughput is achieved by packing two FP16 operations per FP32 lane, a common approach in graphics architectures.

Memory architecture is also identical on paper: both use System Shared memory with a System Shared bus width and System Dependent bandwidth. That means the actual memory performance is dictated by the host platform, not by the GPU itself. In a portable device, the memory subsystem will be shared with the CPU, so the effective bandwidth available to either GPU depends on the system design.

The power architecture is shared as well. Both parts carry a 25 W TDP, use no power connectors, and are integrated into the host package as IGP devices. The display outputs are Portable Device Dependent for both, which reinforces that neither is intended as a discrete add-in card. The production status for both is Active, with the Arc Pro B370 released earlier and the Arc Graphics 2 Xe Mobile released later.

The architectural conclusion from the recorded data is that Intel offers two tiers of the same Xe3-LPG design. The Arc Graphics 2 Xe Mobile is a minimal configuration for basic graphics and media tasks, while the Arc Pro B370 multiplies the execution resources by five in shading units and ray tracing cores, by 2.5x in TMUs, and by 2.5x in ROPs. The higher boost clock on the smaller part does not close the throughput gap, since the larger part's resource count dominates in every fill-rate and compute metric recorded in the database.