Intel Arc Pro B390 vs NVIDIA GeForce RTX 5070 Ti Mobile Comparison

The Verdict

The database contains benchmark data for only one of the two processors: the NVIDIA GeForce RTX 5070 Ti Mobile. The Intel Arc Pro B390 has no recorded benchmark entries, no average score, and no nearest rival comparisons. Consequently, the recorded data supports no direct performance comparison. The NVIDIA part holds an 80th percentile position among all GPUs in the database, with an average benchmark score of 35,435. Its nearest rivals, the NVIDIA Quadro GV100 at 35,520 and the AMD Radeon Pro Duo at 35,860, sit within 1.2% of its score, indicating that the RTX 5070 Ti Mobile lands in a tightly contested performance band. The Intel Arc Pro B390, by contrast, is listed at the 50th percentile with a zero average score, which reflects an absence of measurements rather than a measured performance level.

For anyone selecting between these two parts, the only data-backed choice is the NVIDIA GeForce RTX 5070 Ti Mobile. It delivers measured compute and graphics results across nine separate tests. The Intel Arc Pro B390 cannot be evaluated from the database because it has no benchmark scores. The NVIDIA part also carries a significantly larger measured resource set, including 5,888 shading units, 184 texture mapping units, 80 raster output pipelines, and 46 ray tracing cores. The Intel part provides 1,536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores.

Architecture Differences

The two processors come from different foundries and process nodes. The Intel Arc Pro B390 uses a 3 nm process from Intel, while the NVIDIA GeForce RTX 5070 Ti Mobile uses a 5 nm process from TSMC. Intel builds the B390 on the Panther Lake chip with the Xe3-LPG architecture, placing it in the Arc Graphics-WM (Panther Lake) generation. NVIDIA builds the RTX 5070 Ti Mobile on the GB205 chip with the Blackwell 2.0 architecture, part of the GeForce 50 Mobile generation. The NVIDIA chip contains 31,100 million transistors on a 263 mm² die, producing a transistor density of 118.3 million transistors per square millimeter. Intel does not disclose transistor count, die size, or density for the B390.

Memory architecture differs fundamentally. The Intel part uses system shared memory with a system-dependent bandwidth, meaning its memory size, type, bus width, and bandwidth all depend on the host platform. The NVIDIA part contains 12 GB of GDDR7 memory on a 192-bit bus, delivering 672.0 GB/s of bandwidth. This gives the RTX 5070 Ti Mobile a fixed, dedicated memory pool, whereas the B390 must contend with the host system for memory resources.

Compute resources diverge sharply. The NVIDIA GPU provides 5,888 shading units, 184 TMUs, 80 ROPs, 46 RT cores, and 184 tensor cores. The Intel GPU provides 1,536 shading units, 48 TMUs, 24 ROPs, and 12 RT cores, with no listed tensor core count. Peak FP32 throughput for NVIDIA is 17.04 TFLOPS, while Intel reaches 7.680 TFLOPS. The NVIDIA part maintains FP16 at the same rate, 17.04 TFLOPS with a 1:1 ratio, while Intel achieves 15.36 TFLOPS with a 2:1 ratio. Pixel and texture rates follow the same trend: NVIDIA sustains 115.8 GPixel/s and 266.2 GTexel/s, while Intel manages 60.00 GPixel/s and 120.0 GTexel/s.

Clock behavior also differs. The Intel part has a base clock of 300 MHz and a boost clock of 2500 MHz. The NVIDIA part has a base clock of 847 MHz and a boost clock of 1447 MHz. Despite the higher boost clock on the Intel part, its smaller compute array yields lower peak throughput. Power draw is listed at 80 W for Intel and 60 W for NVIDIA, meaning the RTX 5070 Ti Mobile achieves substantially higher measured performance within a lower power envelope.

Both parts share the same API support: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both use an IGP slot width with no power connectors, and both have portable-device-dependent display outputs. The NVIDIA part uses a PCIe 5.0 x16 bus interface, while the Intel part uses an IGP bus interface. The NVIDIA part released on 2025-02-28 and succeeded the GeForce 40 Mobile. The Intel part released on 2026-01-26 and succeeded the HD Graphics-WM.

Head-to-Head Benchmarks

The database contains no head-to-head benchmark entries for these two processors. The headToHeadBenchmarks array is empty, and the win counts for each side are zero. As a result, no direct comparison of individual test scores can be made between the Intel Arc Pro B390 and the NVIDIA GeForce RTX 5070 Ti Mobile.

The recorded data does include nine benchmark scores for the NVIDIA part. Its Geekbench OpenCL score is 143,870, and its Geekbench Vulkan score is 139,213. Passmark results show 151 for DirectX 10, 237 for DirectX 11, 102 for DirectX 12, 259 for DirectX 9, 981 for G2D, 24,004 for G3D, and 10,101 for GPU compute. These nine scores produce an average benchmark score of 35,435. The Intel Arc Pro B390 has no corresponding scores in any of these tests.

The absence of Intel scores means the database cannot confirm any advantage for either part in a direct test. The NVIDIA part’s nearest rivals provide context for its position. The NVIDIA Quadro GV100 averages 35,520, which is 0.2% higher than the RTX 5070 Ti Mobile. The AMD Radeon Pro Duo averages 35,860, 1.2% higher. The NVIDIA A2 averages 34,690, 2.1% lower. The NVIDIA T1000 averages 36,289, 2.4% higher. The RTX 5070 Ti Mobile therefore sits within a narrow band of roughly 2.4% above or below its closest competitors, with the T1000 ahead and the A2 behind.

FAQ

Q: Does the database show any benchmark scores for the Intel Arc Pro B390?

A: No. The Intel Arc Pro B390 has an empty benchmark array, a zero average benchmark score, and no nearest rivals. It is listed at the 50th percentile among all GPUs, but this reflects the lack of recorded measurements.

Q: What is the average benchmark score for the NVIDIA GeForce RTX 5070 Ti Mobile?

A: The average benchmark score is 35,435, based on nine individual test scores. This places the GPU at the 80th percentile among all GPUs in the database.

Q: How does the RTX 5070 Ti Mobile compare to its nearest rivals?

A: The NVIDIA Quadro GV100 scores 35,520, which is 0.2% higher. The AMD Radeon Pro Duo scores 35,860, 1.2% higher. The NVIDIA A2 scores 34,690, 2.1% lower. The NVIDIA T1000 scores 36,289, 2.4% higher.

Q: Which processor has more shading units?

A: The NVIDIA GeForce RTX 5070 Ti Mobile has 5,888 shading units. The Intel Arc Pro B390 has 1,536 shading units. NVIDIA also leads in TMUs (184 versus 48), ROPs (80 versus 24), and RT cores (46 versus 12).

Q: What memory configuration does each processor use?

A: The Intel Arc Pro B390 uses system shared memory with system-dependent bandwidth. The NVIDIA GeForce RTX 5070 Ti Mobile uses 12 GB of GDDR7 memory on a 192-bit bus with 672.0 GB/s of bandwidth.

Q: What is the peak FP32 throughput for each processor?

A: The NVIDIA GeForce RTX 5070 Ti Mobile reaches 17.04 TFLOPS. The Intel Arc Pro B390 reaches 7.680 TFLOPS. NVIDIA’s FP16 throughput is also 17.04 TFLOPS at a 1:1 ratio, while Intel’s FP16 is 15.36 TFLOPS at a 2:1 ratio.

Where Each One Wins

The NVIDIA GeForce RTX 5070 Ti Mobile wins in every category where the database contains measured data. Its FP32 throughput of 17.04 TFLOPS is more than double the Intel part’s 7.680 TFLOPS. Its texture rate of 266.2 GTexel/s exceeds Intel’s 120.0 GTexel/s, and its pixel rate of 115.8 GPixel/s exceeds Intel’s 60.00 GPixel/s. The NVIDIA part also provides more RT cores (46 versus 12) and adds 184 tensor cores, which the Intel part does not list. Dedicated 12 GB GDDR7 memory with 672.0 GB/s bandwidth gives the NVIDIA GPU a fixed memory advantage over the Intel part’s system-shared memory with system-dependent bandwidth.

The Intel Arc Pro B390 wins on process node, using a 3 nm Intel process versus the 5 nm TSMC process on the NVIDIA part. It also lists a higher boost clock at 2500 MHz versus 1447 MHz, and its FP16 throughput of 15.36 TFLOPS at a 2:1 ratio indicates strong half-precision capability relative to its FP32 rate, though still below NVIDIA’s 17.04 TFLOPS in absolute terms. The Intel part’s 80 W power draw is higher than NVIDIA’s 60 W, so the Intel part does not win on efficiency as recorded. The Intel part also uses an IGP bus interface, whereas the NVIDIA part uses PCIe 5.0 x16, which gives the NVIDIA GPU a more capable external interface for data transfer.

For use cases, the recorded data supports the NVIDIA part for any workload requiring high FP32 compute, ray tracing, tensor operations, or dedicated memory bandwidth. The Intel part’s only measured advantages are its smaller process node and higher boost clock, but neither translates into a benchmark win because no Intel benchmark scores exist. The NVIDIA GPU’s 80th percentile rank and average score of 35,435, with nearest rivals within 2.4%, confirm it operates in a competitive performance class. The Intel part’s 50th percentile rank with no scores provides no basis for a workload recommendation. The database therefore supports the NVIDIA GeForce RTX 5070 Ti Mobile as the only processor with verified performance data, and the Intel Arc Pro B390 as a part whose capabilities remain unmeasured in the database.