Intel Arc Pro B370 vs NVIDIA GeForce RTX 5090 Mobile Comparison

FAQ

Q: What is the performance percentile ranking of each GPU in the database?

A: The Intel Arc Pro B370 sits at the 50th percentile among all GPUs, while the NVIDIA GeForce RTX 5090 Mobile ranks much higher at the 84th percentile. This places the NVIDIA part in the top tier of recorded mobile graphics solutions.

Q: What is the average benchmark score for the RTX 5090 Mobile, and how does it compare to its nearest rivals?

A: The RTX 5090 Mobile records an average benchmark score of 45,152. Its closest competitor, the AMD Radeon Pro 5500 XT, scores 45,384, which is 0.5% higher. The NVIDIA GeForce RTX 4070 Ti scores 44,795, putting it 0.8% behind the RTX 5090 Mobile. The Intel Arc A730M scores 45,592 (1% higher), and the NVIDIA RTX 5880 Ada Generation scores 45,972 (1.8% higher).

Q: What is the TDP difference between the two GPUs?

A: The Intel Arc Pro B370 has a TDP of 25 W, while the NVIDIA GeForce RTX 5090 Mobile has a TDP of 95 W. The NVIDIA part consumes 70 W more power according to the recorded specifications.

Q: What DirectX and Vulkan versions do both GPUs support?

A: Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Their API feature sets are identical in the database.

Q: Does the Intel Arc Pro B370 have any recorded benchmark scores?

A: The database shows no benchmark entries for the Intel Arc Pro B370. Its average benchmark score is recorded as 0, and it has no nearest rivals listed. In contrast, the RTX 5090 Mobile has ten recorded benchmark submissions.

Q: What process nodes are used for each chip?

A: The Intel Arc Pro B370 uses a 3 nm process node fabricated by Intel, while the NVIDIA GeForce RTX 5090 Mobile uses a 5 nm process node from TSMC.

The Verdict

The data indicates a decisive performance gulf between these two mobile GPUs. The NVIDIA GeForce RTX 5090 Mobile records an average benchmark score of 45,152 and sits at the 84th percentile, while the Intel Arc Pro B370 has no recorded benchmark scores and sits at the 50th percentile. Any user requiring measured 3D performance should consider the RTX 5090 Mobile, as it delivers a full suite of benchmark results across DirectX 9 through DirectX 12, OpenCL, Vulkan, and compute workloads.

The Intel Arc Pro B370, with its 25 W TDP and integrated graphics implementation, targets a different usage profile. Its system-shared memory and portable-device-dependent display outputs suggest it is designed for compact, low-power platforms. The RTX 5090 Mobile, with 24 GB of dedicated GDDR7 memory, 896.0 GB/s bandwidth, and a 95 W TDP, is positioned for high-end gaming laptops and professional mobile workstations.

For users who need measured performance data, the RTX 5090 Mobile is the only option with recorded results. For users who prioritize minimal power draw and integrated simplicity, the Arc Pro B370 offers a 25 W solution, but no benchmark evidence exists in the database to validate its performance level.

Head-to-Head Benchmarks

The RTX 5090 Mobile has ten recorded benchmark submissions, while the Arc Pro B370 has none. This makes a direct head-to-head comparison one-sided, but the available data still provides useful context.

In 3DMark Steel Nomad DX12, the RTX 5090 Mobile scores 5,871. This is its most demanding graphics workload in the database. In Geekbench OpenCL, the score reaches 201,834, and in Geekbench Vulkan, it reaches 198,405. These two results show strong compute and graphics API performance respectively.

PassMark results for the RTX 5090 Mobile show 183 in DirectX 10, 269 in DirectX 11, 138 in DirectX 12, and 324 in DirectX 9. The PassMark G3D score is 30,034, while the G2D score is 1,057. The PassMark GPU compute score is 13,401.

The Arc Pro B370 produces no comparable numbers. Its FP32 throughput is recorded at 6.144 TFLOPS, and its FP16 throughput is 12.29 TFLOPS (2:1). The RTX 5090 Mobile delivers 31.80 TFLOPS FP32 and 31.80 TFLOPS FP16 (1:1). The NVIDIA part provides roughly 5.2 times the FP32 throughput based on these figures.

Pixel and texture rates follow the same pattern. The RTX 5090 Mobile achieves 169.7 GPixel/s and 496.9 GTexel/s. The Arc Pro B370 achieves 48.00 GPixel/s and 96.00 GTexel/s. The RTX 5090 Mobile is about 3.5 times faster in pixel throughput and about 5.2 times faster in texture throughput.

The nearest rivals for the RTX 5090 Mobile provide additional context for its average score. The AMD Radeon Pro 5500 XT is 0.5% faster, the Intel Arc A730M is 1% faster, and the NVIDIA RTX 5880 Ada Generation is 1.8% faster. The NVIDIA GeForce RTX 4070 Ti is 0.8% slower. This places the RTX 5090 Mobile in a tight cluster of desktop and mobile GPUs with similar average scores, despite its notebook form factor.

Specification Differences

The RTX 5090 Mobile uses a GB203 chip with 45,600 million transistors on a 378 mm² die, yielding a transistor density of 120.6M per mm². The Arc Pro B370 lists its transistor count and die size as unknown.

Memory configurations differ fundamentally. The RTX 5090 Mobile has 24 GB of GDDR7 on a 256-bit bus with 896.0 GB/s bandwidth and a memory clock of 1750 MHz (28 Gbps effective). The Arc Pro B370 uses system-shared memory with a system-dependent bandwidth and no dedicated memory clock.

The RTX 5090 Mobile has 10,496 shading units, 328 TMUs, 112 ROPs, 82 RT cores, and 328 tensor cores. The Arc Pro B370 has 1,280 shading units, 40 TMUs, 20 ROPs, and 10 RT cores. It lists no tensor cores.

Clock speeds show the RTX 5090 Mobile running at a 990 MHz base and 1515 MHz boost. The Arc Pro B370 runs at a 300 MHz base and 2400 MHz boost. Despite the higher boost clock on the Intel part, its much smaller execution resource count limits overall throughput.

The RTX 5090 Mobile uses a PCIe 5.0 x16 bus interface. The Arc Pro B370 uses an integrated graphics processor (IGP) interface. Both are listed with IGP slot width and no power connectors. The RTX 5090 Mobile carries a 95 W TDP versus 25 W for the Arc Pro B370.

Release dates differ by about ten months. The RTX 5090 Mobile launched on 2025-03-26, and the Arc Pro B370 launched on 2026-01-26. The Intel part lists HD Graphics-WM as its predecessor. The NVIDIA part lists GeForce 40 Mobile as its predecessor.

Architecture Differences

The Arc Pro B370 is built on Intel's Panther Lake chip using the Xe3-LPG architecture, classified under Arc Graphics-WM (Panther Lake). It uses a 3 nm process node from Intel's own foundry. The RTX 5090 Mobile uses NVIDIA's GB203 chip with Blackwell 2.0 architecture, fabricated on a 5 nm process node by TSMC.

The compute resource gap is substantial. The RTX 5090 Mobile packs 10,496 shading units, 328 TMUs, and 112 ROPs. The Arc Pro B370 has 1,280 shading units, 40 TMUs, and 20 ROPs. These are roughly 8.2 times, 8.2 times, and 5.6 times fewer respectively.

Ray tracing hardware differs as well. The RTX 5090 Mobile has 82 RT cores, while the Arc Pro B370 has 10. Tensor core support exists only on the NVIDIA part with 328 tensor cores; the Intel part lists none.

Memory architecture separates the two completely. The RTX 5090 Mobile uses discrete GDDR7 with a 256-bit bus and 896.0 GB/s bandwidth. The Arc Pro B370 relies on system-shared memory with bandwidth dependent on the host platform. This affects every memory-bound workload.

FP16 processing ratios differ. The RTX 5090 Mobile achieves 31.80 TFLOPS FP16 at a 1:1 ratio with FP32. The Arc Pro B370 reaches 12.29 TFLOPS FP16 at a 2:1 ratio, meaning its FP16 throughput is double its FP32 rate. The NVIDIA part uses unified shader throughput, while the Intel part uses a packed math path.

Both GPUs support the same API levels: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The production status for both is Active.

Where Each One Wins

The RTX 5090 Mobile wins in every category with recorded measurements. It has benchmark scores across ten tests, a top-quartile percentile ranking, and an average score of 45,152. Its nearest rivals sit within 1.8% of its average score, confirming it operates at a competitive level against high-end desktop and mobile parts.

The Arc Pro B370 wins on power efficiency targets. Its 25 W TDP is 70 W lower than the RTX 5090 Mobile's 95 W TDP. For platforms constrained by thermals or battery capacity, the Intel part presents a much lighter load. Its 3 nm process node from Intel also represents a more advanced lithography than the 5 nm node used by NVIDIA.

The RTX 5090 Mobile wins on memory capability. Its 24 GB GDDR7 configuration with 896.0 GB/s bandwidth provides dedicated, high-speed storage. The Arc Pro B370's system-shared memory offers no dedicated bandwidth figure, leaving performance dependent on the host system.

The RTX 5090 Mobile wins on raw compute throughput. Its 31.80 TFLOPS FP32 and 31.80 TFLOPS FP16 dwarf the Arc Pro B370's 6.144 TFLOPS FP32 and 12.29 TFLOPS FP16. Its 169.7 GPixel/s pixel rate and 496.9 GTexel/s texture rate similarly exceed the Intel part's 48.00 GPixel/s and 96.00 GTexel/s.

The Arc Pro B370 wins on integration simplicity. It uses an IGP bus interface, requires no power connectors, and relies on system memory. The RTX 5090 Mobile also has no power connectors listed, but its PCIe 5.0 x16 interface and discrete memory require a more substantial host platform.

The RTX 5090 Mobile wins on ray tracing resources with 82 RT cores versus 10. It also has tensor cores for AI workloads, which the Intel part lacks entirely.

The Arc Pro B370 wins on boost clock frequency, reaching 2400 MHz versus 1515 MHz for the RTX 5090 Mobile. This does not translate into higher throughput given the massive gap in execution units, but it does indicate a different design philosophy: fewer, faster units on the Intel side versus many, slower units on the NVIDIA side.

For users selecting between these two, the RTX 5090 Mobile is the only part with measured performance evidence. The Arc Pro B370 offers a low-power integrated alternative, but its performance profile remains unquantified in the database.