Intel Arc 140T Mobile vs Intel Arc B390 Comparison

Head-to-Head Benchmarks

The recorded data for this comparison is asymmetrical. The Intel Arc 140T Mobile has no benchmark entries in the database, while the Intel Arc B390 has one recorded result. Consequently, direct head-to-head scores cannot be established from the database. What the data does show is the Arc B390's absolute performance level and its position against other GPUs.

The Intel Arc B390 produced a score of 1482 in the 3DMark Steel Nomad DX12 test. That result places the part at the 9th percentile among all GPUs in the database. The interpretation is straightforward: the B390 sits in the lower performance tier of the current GPU landscape, a conclusion reinforced by its nearest rivals. The closest competitor is the NVIDIA GeForce GT 520MX, which averages 1463 points, a margin of 1.3% in favor of the B390. The GeForce 800M trails by 1.5% (1460 points), the GeForce GT 625 OEM trails by 2.5% (1446 points), and the GeForce GT 710 trails by 2.7% (1443 points).

These small deltas indicate that the B390's lead over its nearest rivals is narrow. A 1.3% advantage over the GT 520MX is within run-to-run variance for many workloads. The B390 is not dramatically faster than these older parts; it is marginally ahead. The 9th percentile ranking reinforces this: the B390 is not a high-performance part, but it does outperform the four low-end NVIDIA parts listed as its nearest rivals.

The Intel Arc 140T Mobile has no benchmark scores in the database, so its performance cannot be quantified or compared directly. The database records no wins for either part in a head-to-head sense because no paired benchmark results exist. The only measurable performance data belongs to the Arc B390.

FAQ

Q: How does the Intel Arc B390 compare to its nearest rivals in the database?

A: The Arc B390 scored 1482 in 3DMark Steel Nomad DX12. It leads the NVIDIA GeForce GT 520MX by 1.3% (1463 points), the GeForce 800M by 1.5% (1460 points), the GeForce GT 625 OEM by 2.5% (1446 points), and the GeForce GT 710 by 2.7% (1443 points). The deltas are small, indicating a marginal performance edge.

Q: What is the Arc B390's overall performance percentile?

A: The Arc B390 sits at the 9th percentile among all GPUs in the database. This means roughly 91% of recorded GPUs perform better, placing the B390 in the low-performance tier.

Q: Why is there no direct head-to-head comparison between the Arc 140T Mobile and the Arc B390?

A: The database contains no benchmark entries for the Intel Arc 140T Mobile. Its average benchmark score is recorded as 0. Without a measured score, no direct comparison against the Arc B390's 1482-point result is possible.

Q: What are the architectural differences between the two parts?

A: The Arc 140T Mobile uses the Arrow Lake-H chip with Xe-LPG+ architecture on a 5 nm TSMC process. The Arc B390 uses the Panther Lake chip with Xe3-LPG architecture on a 3 nm Intel process. The B390 also has more shading units (1536 vs 1024), more ray tracing cores (12 vs 8), but fewer TMUs (48 vs 64) and ROPs (24 vs 32).

Q: Which part has a higher boost clock?

A: The Intel Arc B390 boosts to 2500 MHz, while the Intel Arc 140T Mobile boosts to 2350 MHz. Both have a 300 MHz base clock.

Q: What is the thermal design power difference?

A: The Arc 140T Mobile has a TDP of 35 W. The Arc B390 has a TDP of 80 W, more than double that of the mobile part.

Architecture Differences

The two GPUs come from different chips and architectures. The Intel Arc 140T Mobile is built on the Arrow Lake-H chip using Xe-LPG+ architecture. The Intel Arc B390 is built on the Panther Lake chip using Xe3-LPG architecture. Both belong to the Arc Graphics-M family, but they represent different generations: the 140T is part of Arc Graphics-M (Arrow Lake), while the B390 is part of Arc Graphics-M (Panther Lake).

The manufacturing processes differ significantly. The Arc 140T Mobile uses a 5 nm process from TSMC. The Arc B390 uses a 3 nm process from Intel. The database does not list transistor counts or die sizes for either part, so density comparisons cannot be made. The foundry shift from TSMC to Intel is a notable architectural change.

Execution resources differ in several ways. The Arc 140T Mobile has 1024 shading units, 64 texture mapping units, and 32 render output units. The Arc B390 has 1536 shading units, 48 TMUs, and 24 ROPs. The B390 has 50% more shading units, but 25% fewer TMUs and 25% fewer ROPs. Ray tracing cores also differ: the B390 has 12, the 140T has 8.

Neither part lists tensor cores in the database. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Memory architecture is identical in type: both use system shared memory with system dependent bandwidth. There is no dedicated VRAM on either part.

The clock behavior shows the B390 boosting higher (2500 MHz vs 2350 MHz), which, combined with the larger shading unit count, explains its higher raw compute figures. The pixel rate, however, favors the 140T: 75.20 GPixel/s vs 60.00 GPixel/s. The texture rate also favors the 140T: 150.4 GTexel/s vs 120.0 GTexel/s. These rate differences stem directly from the higher TMU and ROP counts on the 140T.

Specification Differences

The following specifications differ between the two parts:

• Chip: Arrow Lake-H (140T) vs Panther Lake (B390)
• Architecture: Xe-LPG+ (140T) vs Xe3-LPG (B390)
• Generation: Arc Graphics-M (Arrow Lake) (140T) vs Arc Graphics-M (Panther Lake) (B390)
• Process Node: 5 nm (140T) vs 3 nm (B390)
• Foundry: TSMC (140T) vs Intel (B390)
• Base Clock: 300 MHz (both), but boost differs: 2350 MHz (140T) vs 2500 MHz (B390)
• Shading Units: 1024 (140T) vs 1536 (B390)
• TMUs: 64 (140T) vs 48 (B390)
• ROPs: 32 (140T) vs 24 (B390)
• Ray Tracing Cores: 8 (140T) vs 12 (B390)
• Pixel Rate: 75.20 GPixel/s (140T) vs 60.00 GPixel/s (B390)
• Texture Rate: 150.4 GTexel/s (140T) vs 120.0 GTexel/s (B390)
• FP32 Performance: 4.813 TFLOPS (140T) vs 7.680 TFLOPS (B390)
• FP16 Performance: 9.626 TFLOPS (2:1) (140T) vs 15.36 TFLOPS (2:1) (B390)
• TDP: 35 W (140T) vs 80 W (B390)
• Power Connectors: None listed (140T) vs None (B390)
• Release Date: 2025-01-12 (140T) vs 2026-01-26 (B390)
• Predecessor: HD Graphics-M (140T) vs none listed (B390)

Both parts share the same memory configuration (system shared, system dependent bandwidth), bus interface (IGP), display outputs (portable device dependent), API support (DirectX 12 Ultimate, OpenGL 4.6, Vulkan 1.4), slot width (IGP), and production status (Active). Neither part has a launch MSRP listed in the database.

Where Each One Wins

The Intel Arc B390 wins in raw compute throughput. Its FP32 performance of 7.680 TFLOPS is 59.5% higher than the 140T's 4.813 TFLOPS. FP16 performance follows the same pattern: 15.36 TFLOPS vs 9.626 TFLOPS, a 59.6% advantage. The B390 also has more shading units (1536 vs 1024) and more ray tracing cores (12 vs 8), which are assets for workloads that scale with shader count or ray tracing workloads. The B390's higher boost clock (2500 MHz vs 2350 MHz) contributes to this compute advantage. The B390's 3 nm Intel process node is also newer than the 140T's 5 nm TSMC node, which historically suggests better transistor efficiency per area, though the database does not include transistor density figures to confirm this.

The Intel Arc 140T Mobile wins in pixel throughput and texture throughput. Its 75.20 GPixel/s pixel rate is 25.3% higher than the B390's 60.00 GPixel/s. Its 150.4 GTexel/s texture rate is 25.3% higher than the B390's 120.0 GTexel/s. These advantages come from the 140T's higher TMU count (64 vs 48) and ROP count (32 vs 24). For fill-rate-bound workloads, such as certain 2D rendering or lower-resolution scenarios that depend on pixel output, the 140T has the edge. The 140T also consumes significantly less power at 35 W TDP compared to the B390's 80 W TDP, which makes it the more efficient part from a thermal budget perspective.

The physical design constraints are identical: both are integrated graphics (IGP) with no power connectors listed. Neither part has a suggested PSU rating in the database. The B390's higher TDP suggests it requires a more substantial cooling solution, but the database does not list cooler requirements.

In summary, the B390 is the compute-oriented part with a clear lead in FP32 and FP16 throughput, shading units, and ray tracing cores. The 140T is the fill-rate and efficiency-oriented part, with higher pixel rates, texture rates, and a much lower TDP. The B390's measured benchmark score of 1482 places it just above the NVIDIA GeForce GT 520MX, GeForce 800M, GeForce GT 625 OEM, and GeForce GT 710, but the 140T has no recorded benchmark score to compare.