Intel Arc B390 vs NVIDIA RTX PRO 5000 Blackwell Comparison

Intel Arc B390 is a mobile-class integrated graphics processor built on Intel’s 3 nm process, while NVIDIA RTX PRO 5000 Blackwell is a professional workstation GPU on TSMC’s 5 nm node with 92,200 million transistors. The database places the Arc B390 at the 9th percentile of all GPUs, while the RTX PRO 5000 sits at the 98th percentile. The single shared benchmark, 3DMark Steel Nomad DX12, shows a score of 1482 for the Arc B390 and 9579.5 for the RTX PRO 5000, a delta of -84.5% for the Intel part. The following analysis walks through the recorded data.

FAQ

Q: What are the average benchmark scores for each GPU?

A: The Intel Arc B390 has an average benchmark score of 1482, based on its single recorded 3DMark Steel Nomad DX12 result. The NVIDIA RTX PRO 5000 Blackwell has an average benchmark score of 182109, which includes results from 3DMark Steel Nomad DX12, Geekbench OpenCL, and Geekbench Vulkan.

Q: How do the two GPUs compare in percentile ranking?

A: The Intel Arc B390 ranks in the 9th percentile of all GPUs in the database. The NVIDIA RTX PRO 5000 Blackwell ranks in the 98th percentile, placing it far above the Intel part in overall standing.

Q: What is the closest rival to the Intel Arc B390 in the database?

A: The nearest rival to the Intel Arc B390 is the NVIDIA GeForce GT 520MX, which has an average score of 1463. The Arc B390 leads that card by 1.3%. Other nearby rivals include the NVIDIA GeForce 800M (1460, +1.5%), NVIDIA GeForce GT 625 OEM (1446, +2.5%), and NVIDIA GeForce GT 710 (1443, +2.7%).

Q: What is the closest rival to the NVIDIA RTX PRO 5000 Blackwell?

A: The nearest rival is the NVIDIA A100 SXM4 80 GB, with an average score of 183725. The RTX PRO 5000 trails that card by 0.9%. It also trails the NVIDIA RTX 5000 Ada Generation by 1.4% and the NVIDIA A100 SXM4 40 GB by 2.7%, while leading the NVIDIA GeForce RTX 4090 D by 2.3%.

Q: Do both GPUs support the same graphics APIs?

A: Yes, both the Intel Arc B390 and the NVIDIA RTX PRO 5000 Blackwell support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4 according to the database.

Q: What is the only head-to-head benchmark result recorded?

A: The only direct comparison is 3DMark Steel Nomad DX12. The Intel Arc B390 scores 1482, and the NVIDIA RTX PRO 5000 Blackwell scores 9579.5, giving the NVIDIA card a -84.5% delta relative to the Intel part.

The Verdict

The recorded data points to a clear separation in performance tiers. The Intel Arc B390 is an integrated GPU in the 9th percentile, with a 3DMark Steel Nomad DX12 score of 1482. Its nearest rivals are older integrated and entry-level discrete NVIDIA parts such as the GeForce GT 520MX, GeForce 800M, GeForce GT 625 OEM, and GeForce GT 710, all within 2.7% of its score. Users relying on this GPU would be working with a base-level graphics solution suitable for basic display output and light rendering tasks.

The NVIDIA RTX PRO 5000 Blackwell sits in the 98th percentile and delivers a 3DMark Steel Nomad DX12 score of 9579.5, which is 8097.5 points higher than the Arc B390. Its average benchmark score of 182109 reflects strong OpenCL and Vulkan results as well: Geekbench OpenCL at 254116 and Geekbench Vulkan at 282631. The nearest rivals to the RTX PRO 5000 include the NVIDIA A100 SXM4 80 GB, RTX 5000 Ada Generation, GeForce RTX 4090 D, and A100 SXM4 40 GB, meaning it competes in the top tier of workstation and datacenter-class hardware.

The choice between these two is determined by the workload. The Arc B390 is an IGP with no dedicated memory, no power connectors, and an 80 W TDP, making it appropriate for compact systems where the CPU provides graphics. The RTX PRO 5000 is a dual-slot, 300 W card with 48 GB of GDDR7 memory, a 384 bit bus, and 1.34 TB/s bandwidth, suited for professional rendering, compute, and AI workloads where the extra memory and throughput matter. The database does not record any benchmark where the Intel part wins.

Head-to-Head Benchmarks

The database contains one head-to-head comparison: 3DMark Steel Nomad DX12. In this test, the Intel Arc B390 scores 1482, and the NVIDIA RTX PRO 5000 Blackwell scores 9579.5. The delta is -84.5%, meaning the Arc B390 delivers roughly one-sixth of the NVIDIA card’s score in this particular test. No other shared benchmark results are recorded, so the comparison is limited to this single workload.

For context, the Arc B390’s nearest rivals in the database are the NVIDIA GeForce GT 520MX (1463, +1.3%), GeForce 800M (1460, +1.5%), GeForce GT 625 OEM (1446, +2.5%), and GeForce GT 710 (1443, +2.7%). The Intel part leads all four, but by margins under 3%. This places the Arc B390 in the same performance bracket as those older NVIDIA parts, all of which are far below the RTX PRO 5000.

The RTX PRO 5000’s nearest rivals are all high-end NVIDIA products. The A100 SXM4 80 GB averages 183725, which is 0.9% above the RTX PRO 5000. The RTX 5000 Ada Generation averages 184664, 1.4% above. The GeForce RTX 4090 D averages 178050, 2.3% below the RTX PRO 5000. The A100 SXM4 40 GB averages 187147, 2.7% above. These deltas show that the RTX PRO 5000 performs within a narrow band of some of the most capable NVIDIA accelerators currently recorded.

The Geekbench results for the RTX PRO 5000 further characterize its performance. The OpenCL score is 254116, and the Vulkan score is 282631. No equivalent Geekbench results exist for the Arc B390, so cross-comparison is not possible for those tests. All recorded wins in the head-to-head data belong to the NVIDIA RTX PRO 5000 Blackwell, with 1 win and 0 for the Intel Arc B390.

Specification Differences

The two GPUs differ fundamentally in memory architecture. The Intel Arc B390 uses system shared memory, with the type, bus width, and bandwidth all listed as system dependent. The NVIDIA RTX PRO 5000 has 48 GB of GDDR7 memory on a 384 bit bus with 1.34 TB/s of bandwidth. This is a major separation: the Intel part has no dedicated VRAM, while the NVIDIA card provides a large, high-bandwidth memory pool.

Clock speeds also differ. The Arc B390 has a base clock of 300 MHz and a boost clock of 2500 MHz. The RTX PRO 5000 has a base clock of 1740 MHz and a boost clock of 2377 MHz. Although the Intel part has a higher boost clock, its memory and compute resources are far smaller.

The compute configuration is heavily skewed toward the NVIDIA card. The Arc B390 has 1536 shading units, 48 texture mapping units, 24 ROPs, and 12 ray tracing cores. The RTX PRO 5000 has 14080 shading units, 440 TMUs, 160 ROPs, and 110 ray tracing cores. The NVIDIA card also includes 440 tensor cores, while the Arc B390 has no recorded tensor core count.

Power and physical specifications differ as well. The Arc B390 has an 80 W TDP, is an IGP with no power connectors, and uses an IGP bus interface. The RTX PRO 5000 has a 300 W TDP, is dual-slot, uses a single 16-pin power connector, and connects via PCIe 5.0 x16. The suggested PSU for the RTX PRO 5000 is 700 W. The NVIDIA card measures 267 mm in length, 111 mm in height, and 40 mm in width. The Intel part has no recorded dimensions because it is integrated.

Architecture Differences

The Intel Arc B390 is built on Intel’s 3 nm process and uses the Xe3-LPG architecture. Its chip is codenamed Panther Lake, and the generation is listed as Arc Graphics-M (Panther Lake). The foundry is Intel. Transistor count and die size are not recorded in the database.

The NVIDIA RTX PRO 5000 is built on TSMC’s 5 nm process and uses the Blackwell 2.0 architecture. The chip is GB202, and the generation is Blackwell PRO W (x000). The foundry is TSMC. The transistor count is 92,200 million, the die size is 750 mm², and the transistor density is 122.9M per mm². The predecessor is listed as Workstation Ada.

Memory bandwidth differs at the architectural level. The Arc B390’s memory bandwidth is listed as system dependent, with no fixed figure. The RTX PRO 5000 delivers 1.34 TB/s. The FP32 throughput for the Arc B390 is 7.680 TFLOPS, while the RTX PRO 5000 reaches 66.94 TFLOPS. FP16 performance also differs: the Arc B390 delivers 15.36 TFLOPS at a 2:1 ratio, while the RTX PRO 5000 delivers 66.94 TFLOPS at a 1:1 ratio.

Pixel and texture rates reflect the resource gap. The Arc B390 has a pixel rate of 60.00 GPixel/s and a texture rate of 120.0 GTexel/s. The RTX PRO 5000 has a pixel rate of 380.3 GPixel/s and a texture rate of 1,045.9 GTexel/s. The NVIDIA card also supports 4x DisplayPort 2.1b outputs, while the Arc B390’s display outputs are listed as portable device dependent.

Where Each One Wins

The Intel Arc B390 wins in power efficiency and integration. Its 80 W TDP is dramatically lower than the RTX PRO 5000’s 300 W. It requires no power connectors and no separate graphics card slot, since it is an IGP. For systems where discrete graphics is not an option, the Arc B390 provides DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4 support in an integrated package. It also has a higher boost clock at 2500 MHz compared to 2377 MHz for the NVIDIA card, though this does not translate to a benchmark win.

The NVIDIA RTX PRO 5000 wins in every recorded performance metric. Its 3DMark Steel Nomad DX12 score of 9579.5 is 84.5% higher than the Arc B390’s 1482. Its average benchmark score of 182109 is orders of magnitude above the Arc B390’s 1482. It provides 48 GB of GDDR7 memory, 1.34 TB/s bandwidth, 110 ray tracing cores, 440 tensor cores, and 66.94 TFLOPS of FP32 performance. The Arc B390 has no recorded tensor cores and only 12 ray tracing cores.

In terms of competitive positioning, the Arc B390 sits alongside NVIDIA GeForce GT 520MX, GeForce 800M, GeForce GT 625 OEM, and GeForce GT 710, all within 2.7% of its score. The RTX PRO 5000 sits alongside NVIDIA A100 SXM4 80 GB, RTX 5000 Ada Generation, GeForce RTX 4090 D, and A100 SXM4 40 GB, with deltas between -2.7% and +2.3%. The recorded data indicates that the RTX PRO 5000 is intended for high-end workstation tasks, while the Arc B390 serves as an integrated solution for portable or low-power devices. The wins column shows 0 for the Intel part and 1 for the NVIDIA part in direct comparison.