Intel Arc Pro B390 vs NVIDIA GeForce RTX 5070 Mobile Comparison

Head-to-Head Benchmarks

The recorded data shows a stark contrast between these two mobile graphics solutions, but the comparison is limited by the fact that the Intel Arc Pro B390 has no benchmark entries in the database. The NVIDIA GeForce RTX 5070 Mobile, by contrast, has a full set of nine benchmark scores across compute, graphics, and API-specific tests. Its average benchmark score sits at 29,928, which places it at the 75th percentile of all GPUs in the database. This is a strong position, as it lands within 1.7% of the AMD Radeon RX 6700 (30,433, delta -1.7%) and just 0.1% behind the NVIDIA GeForce RTX 3070 Ti (29,945, delta -0.1%). The RTX 5070 Mobile also edges out the RTX 2080 Ti (29,783, delta 0.5%) and the RX 6800 (30,095, delta -0.6%) by slim margins.

The GeForce RTX 5070 Mobile delivers 13.13 TFLOPS of FP32 compute, which is a direct measure of raw shader throughput. Its peak pixel rate is 68.40 GPixel/s, and its texture rate is 205.2 GTexel/s. These figures come from 4608 shading units, 144 texture mapping units, and 48 raster output units. The GPU also includes 36 ray tracing cores and 144 tensor cores, enabling hardware-accelerated ray tracing and AI-based features. In the Geekbench OpenCL test, the RTX 5070 Mobile scores 122,238, while its Vulkan score is 116,960. The Passmark suite shows a G3D score of 20,355, a GPU compute score of 8,279, and DirectX 12 performance at 93, DirectX 11 at 192, DirectX 10 at 129, and DirectX 9 at 214. The G2D score is 896.

The Intel Arc Pro B390, on the other hand, has zero recorded benchmarks and an average benchmark score of 0. Its percentile rank is 50, which is a neutral midpoint rather than a performance indicator, since no data supports a measured position. The database has no head-to-head benchmark comparisons between the two, and the wins tally shows 0 for both sides. This means that any direct performance comparison must rely entirely on the architectural and specification differences listed below, not on measured results. The RTX 5070 Mobile is clearly the only one of the two with empirical performance data, while the Arc Pro B390 remains a specification-only entry.

Where Each One Wins

Based on the available data, the NVIDIA GeForce RTX 5070 Mobile wins in every measurable category because it is the only one with recorded scores. Its FP32 throughput of 13.13 TFLOPS is 71% higher than the Arc Pro B390's 7.680 TFLOPS, which is a substantial lead in raw compute. The RTX 5070 Mobile also has a higher pixel rate (68.40 GPixel/s versus 60.00 GPixel/s) and a much higher texture rate (205.2 GTexel/s versus 120.0 GTexel/s). These differences indicate that the NVIDIA part is faster in both fill-rate-limited and texture-bound workloads.

The RTX 5070 Mobile also has a significant advantage in ray tracing resources, with 36 RT cores against the Arc Pro B390's 12, and 144 tensor cores against the Arc's null tensor core count. This makes the NVIDIA solution more capable for ray-traced rendering and AI-accelerated tasks. The Arc Pro B390, however, has a higher boost clock: 2500 MHz versus 1425 MHz for the RTX 5070 Mobile. This does not translate into a win in the database, as there is no benchmark to confirm its impact, but it is a specification difference that could matter in certain workloads.

The Intel part also has a lower base clock at 300 MHz, which is notably lower than the NVIDIA's 907 MHz, but the boost clock advantage suggests a wider dynamic range. The Arc Pro B390 uses system-shared memory, meaning its memory size, type, and bus width are all dependent on the host system. In contrast, the RTX 5070 Mobile has 8 GB of dedicated GDDR7 memory on a 128-bit bus, with a bandwidth of 384.0 GB/s. This dedicated memory allocation is a clear win for the NVIDIA part in scenarios where memory bandwidth or capacity is a limiting factor.

Architecture Differences

The Intel Arc Pro B390 is built on the Panther Lake chip using the Xe3-LPG architecture, fabricated on a 3 nm process at Intel's own foundry. The NVIDIA GeForce RTX 5070 Mobile uses the GB206 chip with the Blackwell 2.0 architecture, manufactured on a 5 nm process by TSMC. The process node difference is notable: Intel uses a more advanced 3 nm node, while NVIDIA uses 5 nm. The NVIDIA chip has 21,900 million transistors on a die size of 181 mm², giving a transistor density of 121.0 million per mm². The Intel chip's transistor count and die size are listed as unknown in the database.

The Intel Arc Pro B390 belongs to the Arc Graphics-WM generation (Panther Lake), while the RTX 5070 Mobile is part of the GeForce 50 Mobile generation. The Intel part's predecessor is HD Graphics-WM, and the NVIDIA part's predecessor is GeForce 40 Mobile. Both are currently in Active production status.

The RTX 5070 Mobile has 4608 shading units, 144 TMUs, 48 ROPs, 36 RT cores, and 144 tensor cores. The Arc Pro B390 has 1536 shading units, 48 TMUs, 24 ROPs, and 12 RT cores, with no tensor cores listed. This is a fundamental architectural difference: the NVIDIA GPU is designed with a much larger execution resource pool and dedicated tensor hardware, while the Intel part is more modest in scale and lacks tensor cores entirely. The FP16 performance also differs: the Arc Pro B390 delivers 15.36 TFLOPS at a 2:1 ratio, while the RTX 5070 Mobile delivers 13.13 TFLOPS at a 1:1 ratio. This means the Intel part can double its FP32 throughput for FP16 workloads, whereas the NVIDIA part maintains the same throughput.

Specification Differences

The two GPUs differ across nearly every specification field. The most obvious is memory: the RTX 5070 Mobile has 8 GB of GDDR7 on a 128-bit bus with 384.0 GB/s bandwidth, while the Arc Pro B390 uses system-shared memory with no dedicated size, type, or bus width, and bandwidth is listed as system dependent. The RTX 5070 Mobile's memory clock is 1500 MHz (24 Gbps effective), whereas the Arc's memory clock is also listed as system shared.

Clock speeds differ significantly. The Arc Pro B390 has a base clock of 300 MHz and a boost clock of 2500 MHz. The RTX 5070 Mobile has a base clock of 907 MHz and a boost clock of 1425 MHz. The Intel part has a higher boost, but the NVIDIA part has a higher base.

Power consumption is another differentiator. The Arc Pro B390 has a TDP of 80 W, while the RTX 5070 Mobile has a TDP of 50 W. This is counterintuitive given the RTX 5070 Mobile's larger execution resources, but the data records it as such. Both are IGP slot width with no power connectors, and display outputs are portable device dependent for both.

The bus interface differs: the Arc Pro B390 uses IGP, while the RTX 5070 Mobile uses PCIe 5.0 x16. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The release dates differ as well: the RTX 5070 Mobile was released on 2025-04-14, and the Arc Pro B390 on 2026-01-26. Neither has a launch MSRP in the database.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The NVIDIA GeForce RTX 5070 Mobile, with 13.13 TFLOPS, versus 7.680 TFLOPS for the Intel Arc Pro B390.

Q: What is the memory configuration of each GPU?

A: The RTX 5070 Mobile has 8 GB of GDDR7 on a 128-bit bus with 384.0 GB/s bandwidth. The Arc Pro B390 uses system-shared memory with system-dependent bandwidth.

Q: How do the ray tracing cores compare?

A: The RTX 5070 Mobile has 36 RT cores, while the Arc Pro B390 has 12 RT cores.

Q: Do both GPUs support the same APIs?

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

Q: What is the TDP difference?

A: The Arc Pro B390 has a TDP of 80 W, while the RTX 5070 Mobile has a TDP of 50 W.

Q: Which GPU has a higher boost clock?

A: The Intel Arc Pro B390 has a boost clock of 2500 MHz, compared to 1425 MHz for the RTX 5070 Mobile.

The Verdict

The data confirms a one-sided comparison in terms of measured performance. The NVIDIA GeForce RTX 5070 Mobile has a full set of benchmark scores, an average score of 29,928, and a 75th percentile ranking, with rivals within a 1.7% band. The Intel Arc Pro B390 has no benchmarks, no average score, and a neutral 50th percentile that reflects missing data, not capability.

For users who need proven performance in compute, graphics, and ray tracing, the recorded measurements point exclusively to the RTX 5070 Mobile. Its 13.13 TFLOPS FP32, 384.0 GB/s memory bandwidth, and 36 RT cores provide a complete package. The Arc Pro B390 offers a higher boost clock and a lower power draw? no, it has higher TDP at 80 W. The Arc's only numerical advantages are its 3 nm process node and its FP16 throughput of 15.36 TFLOPS at 2:1 ratio.

The choice depends on whether the user prioritizes measured results or architectural novelty. The RTX 5070 Mobile is the only one with empirical evidence of performance. The Arc Pro B390 remains a specification sheet without benchmark validation. Based on the database, the RTX 5070 Mobile is the clear pick for any workload where scores matter.