Intel Arc 130T Mobile vs Intel Arc B390 Comparison

Head-to-Head Benchmarks

The recorded data for the Intel Arc 130T Mobile contains no benchmark entries, while the Intel Arc B390 holds a single score from the 3DMark Steel Nomad DX12 test. That score is 1482 points, placing the Arc B390 at the 9th percentile among all GPUs in the database. The Arc 130T Mobile sits at the 50th percentile, though this figure is derived from its metric profile rather than a comparable workload score. Direct head-to-head numbers are therefore unavailable, but the existing Arc B390 result can still be interpreted against its nearest rivals.

The Arc B390 edges out the NVIDIA GeForce GT 520MX, which averages 1463 points, by 1.3%. It also leads the NVIDIA GeForce 800M by 1.5% (1460 points), the NVIDIA GeForce GT 625 OEM by 2.5% (1446 points), and the NVIDIA GeForce GT 710 by 2.7% (1443 points). These margins are narrow, which suggests the Arc B390 delivers performance in the same class as those legacy discrete parts, despite being an integrated processor. The 1482-point result is the only concrete workload measurement in this comparison, so the Arc 130T Mobile cannot be positioned against the Arc B390 using identical test conditions.

What the data does show is a difference in absolute compute throughput. The Arc B390 reaches 7.680 TFLOPS of FP32 performance, nearly double the 3.942 TFLOPS of the Arc 130T Mobile. That is a 94.8% advantage in raw floating-point rate. The Arc 130T Mobile counters in texture and pixel throughput: its texture rate of 123.2 GTexel/s exceeds the Arc B390's 120.0 GTexel/s, and its pixel rate of 61.60 GPixel/s beats 60.00 GPixel/s. These are small but real wins for the smaller part.

Clock behavior also differs. Both share a 300 MHz base clock, but the Arc B390 boosts to 2500 MHz, while the Arc 130T Mobile reaches 2200 MHz. The Arc B390 therefore runs 300 MHz higher at peak boost, which contributes to its FP32 lead when combined with a larger execution resource pool.

Where Each One Wins

The Arc B390 wins on raw compute density. Its FP32 figure of 7.680 TFLOPS is the highest single throughput number in this comparison, and its FP16 rate of 15.36 TFLOPS (2:1) likewise doubles the Arc 130T Mobile's 7.885 TFLOPS. Workloads that scale with shading units, such as general-purpose compute or heavy pixel shaders, should favor the Arc B390. It also carries more ray tracing cores: 12 versus 7, which indicates a structural advantage for ray-traced scenes, though no ray tracing benchmark score exists in the pack to confirm real-world impact.

The Arc 130T Mobile wins on efficiency-oriented traits. Its TDP is 35 W versus 80 W for the Arc B390, a reduction of 45 W. For a mobile or integrated context, that lower power envelope is meaningful. It also holds a slight edge in pixel fill rate (61.60 GPixel/s) and texture fill rate (123.2 GTexel/s), which could benefit simple 2D workloads or texture-bound scenarios. The Arc 130T Mobile uses a 5 nm TSMC process, whereas the Arc B390 uses Intel's 3 nm node; process differences do not directly translate into workload wins, but they do affect power and density characteristics.

The Arc 130T Mobile also has a higher percentile ranking (50th versus 9th), which reflects its overall standing in the database's broader GPU distribution. However, that ranking is not tied to a specific benchmark score in the pack, so it should be treated as a positional metric rather than a performance comparison against the Arc B390. In terms of software feature support, both parts expose the same API set: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. No API-level advantage exists for either product.

Architecture Differences

The two products come from different architectural generations. The Intel Arc 130T Mobile uses the Xe-LPG+ architecture built around the Arrow Lake-H chip. The Intel Arc B390 uses the newer Xe3-LPG architecture on the Panther Lake chip. This generation gap explains several structural differences. The Arc 130T Mobile is manufactured on a 5 nm process at TSMC, while the Arc B390 uses a 3 nm process at Intel's own foundry.

Execution resources diverge sharply. The Arc 130T Mobile packs 896 shading units, 56 texture mapping units, 28 raster output units, and 7 ray tracing cores. The Arc B390 has 1536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores. So the Arc B390 carries 640 more shading units and 5 more ray tracing cores, but the Arc 130T Mobile has 8 more TMUs and 4 more ROPs. This explains why the Arc B390 dominates FP32 throughput while the Arc 130T Mobile holds a narrow fill-rate lead.

Both products report unknown transistor counts and die sizes, so no density comparison is possible from the data. The memory subsystem is identical in description: system shared memory, system shared type, system shared bus width, and system-dependent bandwidth. Neither part has dedicated VRAM, which is typical for integrated graphics. The Arc B390 lists no power connectors, consistent with an IGP design, and both use the IGP bus interface. Display outputs for both are listed as portable device dependent.

The release timeline also differs. The Arc 130T Mobile launched on January 12, 2025, while the Arc B390 arrived on January 26, 2026, roughly a year later. The Arc 130T Mobile lists a predecessor, HD Graphics-M, while the Arc B390 has no predecessor entry in the database. Production status is active for both.

Specification Differences

The most consequential specification gap is shading unit count: 896 for the Arc 130T Mobile versus 1536 for the Arc B390. That difference drives the FP32 and FP16 output. The Arc B390's FP32 of 7.680 TFLOPS and FP16 of 15.36 TFLOPS dwarf the Arc 130T Mobile's 3.942 TFLOPS and 7.885 TFLOPS.

Texture and raster resources favor the older part. The Arc 130T Mobile has 56 TMUs and 28 ROPs, while the Arc B390 has 48 TMUs and 24 ROPs. The resulting fill rates are close: 123.2 GTexel/s versus 120.0 GTexel/s for texture, and 61.60 GPixel/s versus 60.00 GPixel/s for pixels. The Arc 130T Mobile leads by 3.2 GTexel/s and 1.60 GPixel/s, respectively.

Ray tracing resources favor the Arc B390 with 12 RT cores against 7. Boost clocks differ by 300 MHz (2500 MHz versus 2200 MHz), while base clocks match at 300 MHz. Power draw is a major split: 35 W for the Arc 130T Mobile, 80 W for the Arc B390. Process node and foundry also differ: 5 nm TSMC versus 3 nm Intel.

The Arc B390 has a measurable benchmark result (1482 in 3DMark Steel Nomad DX12) and an average benchmark score of 1482, while the Arc 130T Mobile has no benchmark entries and an average score of 0. Percentile placement differs as well: 9th for the Arc B390, 50th for the Arc 130T Mobile. No launch MSRP exists for either product in the database, and neither has a successor listed. The Arc 130T Mobile has a predecessor (HD Graphics-M); the Arc B390 does not.

FAQ

Q: Which GPU has more shading units?

A: The Intel Arc B390 has 1536 shading units, compared to 896 for the Intel Arc 130T Mobile.

Q: What is the FP32 performance of each GPU?

A: The Arc B390 delivers 7.680 TFLOPS of FP32 compute, while the Arc 130T Mobile delivers 3.942 TFLOPS.

Q: Does the Arc 130T Mobile have any fill rate advantage?

A: Yes. The Arc 130T Mobile reaches 61.60 GPixel/s and 123.2 GTexel/s, while the Arc B390 reaches 60.00 GPixel/s and 120.0 GTexel/s.

Q: What is the Arc B390's 3DMark Steel Nomad DX12 score?

A: The Arc B390 scored 1482 points, which puts it 1.3% ahead of the NVIDIA GeForce GT 520MX (1463 points) and 2.7% ahead of the NVIDIA GeForce GT 710 (1443 points).

Q: How do the power requirements differ?

A: The Arc 130T Mobile has a TDP of 35 W, while the Arc B390 has a TDP of 80 W.

Q: Do both GPUs support the same APIs?

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