Intel Arc B390 vs NVIDIA RTX 5000 Mobile Ada Generation Comparison

Intel Arc B390 and NVIDIA RTX 5000 Mobile Ada Generation occupy different tiers of the mobile graphics landscape, and the benchmark data reflects a clear separation in raw compute capability. The Arc B390, built for integrated use in Panther Lake platforms, scores 1482 in 3DMark Steel Nomad DX12, placing it at the 9th percentile of all GPUs. The RTX 5000 Mobile Ada Generation, a discrete-class part with 16 GB of GDDR6, scores 3596 in the same test, landing at the 21st percentile. The head-to-head delta is 58.8% in favor of the NVIDIA part. These results establish the RTX 5000 as the substantially faster option for sustained 3D workloads, while the Arc B390 serves a fundamentally different role.

The Verdict

The NVIDIA RTX 5000 Mobile Ada Generation is the clear performance pick based on the recorded data. It delivers a 58.8% higher score in 3DMark Steel Nomad DX12 compared to the Intel Arc B390, a margin that separates the two into different usability classes for graphics-intensive applications. The RTX 5000 also carries 9728 shading units, 304 tensor cores, and 41.15 TFLOPS of FP32 compute, figures that dwarf the Arc B390's 1536 shading units and 7.680 TFLOPS. Any workload that relies on raw shading throughput, ray tracing, or tensor acceleration will favor the NVIDIA part overwhelmingly.

The Intel Arc B390 is not without purpose. It is an integrated graphics processor with an 80 W TDP, designed for portable devices where a discrete GPU is not an option. Its 1482 Steel Nomad score places it near the NVIDIA GeForce GT 520MX, which averages 1463, a 1.3% difference. It also edges out the GeForce 800M by 1.5% and the GT 625 OEM by 2.5%. For a user constrained to an integrated solution, the Arc B390 offers competitive performance within that narrow class. The data does not support choosing it over the RTX 5000 for any performance-driven scenario, but it does show it as a viable IGP option.

FAQ

Q: Which GPU has the higher 3DMark Steel Nomad DX12 score?

A: The NVIDIA RTX 5000 Mobile Ada Generation scores 3596, while the Intel Arc B390 scores 1482. The NVIDIA part leads by 58.8% in the head-to-head comparison.

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

A: The Arc B390 scores 1.3% higher than the NVIDIA GeForce GT 520MX, 1.5% higher than the GeForce 800M, 2.5% higher than the GT 625 OEM, and 2.7% higher than the GT 710.

Q: What memory configuration does each GPU use?

A: The RTX 5000 Mobile Ada Generation uses 16 GB of GDDR6 on a 256-bit bus with 576.0 GB/s bandwidth. The Intel Arc B390 uses system shared memory, with bandwidth described as system dependent.

Q: Which GPU has more shading units and ray tracing cores?

A: The RTX 5000 Mobile Ada Generation has 9728 shading units and 76 ray tracing cores. The Intel Arc B390 has 1536 shading units and 12 ray tracing cores.

Q: What are the power targets of these two GPUs?

A: The Intel Arc B390 has a TDP of 80 W. The NVIDIA RTX 5000 Mobile Ada Generation has a TDP of 120 W.

Q: What is the manufacturing process for each chip?

A: The Intel Arc B390 uses a 3 nm process fabricated by Intel. The NVIDIA RTX 5000 Mobile Ada Generation uses a 5 nm process fabricated by TSMC.

Architecture Differences

The Intel Arc B390 is built on Intel's Xe3-LPG architecture and is part of the Arc Graphics-M generation for Panther Lake. It uses a 3 nm process from Intel's own foundry. The chip integrates 1536 shading units, 48 texture mapping units, and 24 ROPs. Ray tracing is handled by 12 dedicated RT cores. Tensor cores are not listed for this part, meaning AI acceleration relies on other resources within the integrated design. The architecture supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

The NVIDIA RTX 5000 Mobile Ada Generation uses the Ada Lovelace architecture with the AD103 chip, fabricated on a 5 nm process by TSMC. The die contains 45,900 million transistors across 379 mm², giving a transistor density of 121.1M per mm². It packs 9728 shading units, 304 TMUs, and 112 ROPs. Ray tracing is handled by 76 RT cores, and tensor acceleration by 304 tensor cores. The API support matches the Intel part: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The predecessor is listed as Ampere-MW, and the successor is Blackwell-MW.

The core philosophy differs significantly. The Arc B390 is an integrated solution sharing system memory, while the RTX 5000 is a high-throughput discrete-class design with dedicated GDDR6. The presence of 304 tensor cores on the NVIDIA part versus none listed on the Intel part points to a wide gap in AI-oriented tasks. The RTX 5000 also carries a much larger execution resource pool, which explains its commanding lead in the Steel Nomad benchmark.

Specification Differences

The two GPUs diverge on nearly every measurable specification. The Intel Arc B390 operates at a base clock of 300 MHz and a boost clock of 2500 MHz. The RTX 5000 Mobile Ada Generation runs at a base clock of 1425 MHz and a boost clock of 2115 MHz. The Intel part has a lower base clock but a higher boost ceiling, though its shading unit count is far smaller.

Memory is a major differentiator. The Arc B390 uses system shared memory with a system-dependent bandwidth. The RTX 5000 has 16 GB of GDDR6 on a 256-bit bus, delivering 576.0 GB/s of bandwidth. The memory clock for the NVIDIA part is listed as 2250 MHz with 18 Gbps effective speed.

Compute rates show the scale of the gap. The Arc B390 produces 7.680 TFLOPS of FP32 and 15.36 TFLOPS of FP16 at a 2:1 ratio. The RTX 5000 achieves 41.15 TFLOPS of FP32 and 41.15 TFLOPS of FP16 at a 1:1 ratio. Pixel rate for the Intel part is 60.00 GPixel/s, while the NVIDIA part reaches 236.9 GPixel/s. Texture rate is 120.0 GTexel/s for the Arc B390 and 643.0 GTexel/s for the RTX 5000.

Power and interface also differ. The Arc B390 has an 80 W TDP and connects via an IGP bus interface. The RTX 5000 has a 120 W TDP and uses PCIe 4.0 x16. Both are listed as IGP slot width with no power connectors and portable-device-dependent display outputs. The Arc B390 released on 2026-01-26, while the RTX 5000 released on 2023-03-20. Both are marked as Active in production status.

Head-to-Head Benchmarks

The only direct comparison in the database is the 3DMark Steel Nomad DX12 test. The Intel Arc B390 scores 1482, and the NVIDIA RTX 5000 Mobile Ada Generation scores 3596. The delta is 58.8% in favor of the NVIDIA part. This is not a narrow win; it is a dominant margin that holds across the entire execution pipeline.

Context from nearest rivals reinforces the placement. The Arc B390's 1482 score sits just above the GeForce GT 520MX's 1463, a 1.3% edge, and above the GeForce 800M at 1460, a 1.5% edge. The RTX 5000's 3596 score is nearly identical to the GeForce GT 545 at 3594, a 0.1% difference, and slightly below the GT 735M at 3616, a 0.6% deficit. These nearest-rival comparisons show that both GPUs sit in their respective performance bands, but those bands are far apart.

The head-to-head winner is the NVIDIA RTX 5000 Mobile Ada Generation with one win and zero losses. The Intel Arc B390 records zero wins in the comparison. The benchmark result is the single strongest piece of evidence for the performance hierarchy between these two parts.

Where Each One Wins

The NVIDIA RTX 5000 Mobile Ada Generation wins every measured benchmark category against the Arc B390. Its 58.8% lead in Steel Nomad DX12 translates directly to better frame rates in DirectX 12 titles. The 41.15 TFLOPS of FP32 compute, 236.9 GPixel/s pixel rate, and 643.0 GTexel/s texture rate indicate strength in high-resolution rendering, heavy post-processing, and texture-heavy scenes. The 304 tensor cores give it an advantage in workloads that leverage AI acceleration. The 576.0 GB/s of dedicated memory bandwidth removes the bottleneck of system shared memory, which is critical for large textures and data sets.

The Intel Arc B390 wins in the context of its own class. As an integrated GPU with an 80 W TDP, it posts a Steel Nomad score of 1482, which is higher than several older discrete NVIDIA parts including the GT 520MX, the 800M, the GT 625 OEM, and the GT 710. For a laptop or portable device without a discrete GPU option, the Arc B390 delivers a baseline level of 3D performance that outpaces those aging solutions. Its 3 nm process and Intel foundry production indicate a modern manufacturing approach, and its 2500 MHz boost clock is higher than the RTX 5000's 2115 MHz boost, though the raw resource count limits the practical impact of that clock advantage.

Users who need maximum graphics throughput should look to the RTX 5000 Mobile Ada Generation. Users confined to integrated graphics will find the Arc B390 a capable option relative to its direct peers. The data does not suggest any scenario where the Arc B390 outperforms the RTX 5000, but it does confirm the Arc B390 as a solid entry in the integrated segment.