Intel Arc B370 vs NVIDIA GeForce RTX 5090 Mobile Comparison

The Intel Arc B370 and the NVIDIA GeForce RTX 5090 Mobile represent two very different approaches to integrated graphics in portable devices. The Arc B370 is a low-power, system-shared solution built into Intel’s Panther Lake processor, while the RTX 5090 Mobile is a high-end discrete GPU with dedicated memory and a much larger power envelope. The recorded data shows a decisive performance gap between them, but the specifics of that gap, the architectural reasons behind it, and the use-case implications are worth examining in detail.

Head-to-Head Benchmarks

The only direct comparison available in the database is the 3DMark Steel Nomad DX12 test. This is a demanding modern benchmark that stresses the GPU with DirectX 12 workloads, and the results are starkly one-sided. The Intel Arc B370 scores 1184 points, while the NVIDIA GeForce RTX 5090 Mobile scores 5871 points. The delta is -79.8 percent for the Arc B370, meaning the Intel part delivers roughly one-fifth of the NVIDIA GPU’s performance in this test. The RTX 5090 Mobile is the clear winner in this head-to-head, and the margin is substantial enough to define the entire comparison.

Looking at the broader database context, the Arc B370’s single benchmark score places it at the 5th percentile of all GPUs. Its nearest rivals in the database are the ATI Mobility Radeon HD 5570, which scores 1186, the ATI Radeon HD 5770 at 1190, and the AMD Radeon HD 7650M at 1192. The Arc B370 trails these by -0.2, -0.5, and -0.7 percent respectively. It does beat the AMD FirePro M2000, which scores 1168, by 1.4 percent. These are extremely small deltas, indicating that the Arc B370 sits in a performance class with decade-old discrete mobile GPUs. Its average benchmark score is 1184, and that is the only benchmark recorded for it.

The RTX 5090 Mobile, by contrast, sits at the 84th percentile of all GPUs. Its average benchmark score across all recorded tests is 45152, a figure that includes the 3DMark Steel Nomad result plus several other workloads. Its nearest rivals are the AMD Radeon Pro 5500 XT at 45384, the NVIDIA GeForce RTX 4070 Ti at 44795, the Intel Arc A730M at 45592, and the NVIDIA RTX 5880 Ada Generation at 45972. The RTX 5090 Mobile trails these by -0.5, beats the RTX 4070 Ti by 0.8 percent, and trails the Arc A730M and RTX 5880 Ada Generation by -1 and -1.8 percent respectively. This places it in the same performance neighborhood as desktop-class GPUs from previous generations, a completely different tier from the Arc B370.

The passmark data for the RTX 5090 Mobile further illustrates its range. It scores 30034 in Passmark G3D, 13401 in Passmark GPU Compute, 1057 in Passmark G2D, 324 in Passmark DirectX 9, 269 in Passmark DirectX 11, 183 in Passmark DirectX 10, and 138 in Passmark DirectX 12. The Geekbench OpenCL score is 201834, and the Geekbench Vulkan score is 198405. The Arc B370 has no comparable data in these tests, so the head-to-head remains limited to the single 3DMark result, but that result alone establishes the performance hierarchy.

Where Each One Wins

The RTX 5090 Mobile wins in every measurable category. It has more shading units, more texture mapping units, more render output units, more ray tracing cores, and more tensor cores. Its compute throughput is far higher, as shown by the FP32 rating of 31.80 TFLOPS versus 6.144 TFLOPS for the Arc B370. The RTX 5090 Mobile also delivers higher pixel and texture rates, with 169.7 GPixel/s and 496.9 GTexel/s compared to 48.00 GPixel/s and 96.00 GTexel/s for the Arc B370.

The memory situation is a major differentiator. The RTX 5090 Mobile uses 24 GB of GDDR7 memory on a 256-bit bus, providing 896.0 GB/s of bandwidth. The Arc B370 uses system-shared memory, with bandwidth described as system dependent. This means the Arc B370’s memory performance depends entirely on the host system’s RAM configuration, which introduces variability that the dedicated VRAM of the RTX 5090 Mobile avoids. For workloads that are bandwidth-sensitive, such as high-resolution textures or large compute buffers, the RTX 5090 Mobile has a structural advantage that no system configuration can close.

The Arc B370 does have one advantage: power consumption. Its TDP is 25 W, compared to 95 W for the RTX 5090 Mobile. Both are classified as IGP in slot width, meaning neither uses a discrete slot, but the power draw difference is substantial. The Arc B370’s lower power requirement makes it suitable for thin-and-light systems where battery life and thermal limits are primary concerns. The RTX 5090 Mobile, with its 95 W TDP, requires a larger cooling solution and a more robust power delivery system, which typically means a thicker chassis. However, the database does not record any thermal or battery life measurements, so any claims about real-world efficiency must be limited to the TDP figures themselves.

Architecture Differences

The two GPUs come from entirely different architectural lineages. The Intel Arc B370 is built on the Xe3-LPG architecture, part of the Arc Graphics-M (Panther Lake) generation. It uses a 3 nm process node from Intel’s own foundry. The NVIDIA GeForce RTX 5090 Mobile is based on the Blackwell 2.0 architecture, part of the GeForce 50 Mobile generation, and uses a 5 nm process node from TSMC. The transistor counts differ enormously: the RTX 5090 Mobile has 45,600 million transistors on a 378 mm² die, yielding a transistor density of 120.6 million per mm². The Arc B370’s transistor count and die size are listed as unknown in the database, so no direct density comparison is possible.

The core configurations reflect the performance gap. The Arc B370 has 1280 shading units, 40 TMUs, 20 ROPs, and 10 ray tracing cores. The RTX 5090 Mobile has 10496 shading units, 328 TMUs, 112 ROPs, and 82 ray tracing cores. The RTX 5090 Mobile also includes 328 tensor cores, while the Arc B370’s tensor core count is listed as null. The FP16 throughput tells a similar story: the Arc B370 delivers 12.29 TFLOPS with a 2:1 ratio, while the RTX 5090 Mobile delivers 31.80 TFLOPS with a 1:1 ratio. The 1:1 ratio on the RTX 5090 Mobile means it does not sacrifice half-rate FP16 performance, which is relevant for workloads that mix precision modes.

Clock speeds also differ. The Arc B370 has a base clock of 300 MHz and a boost clock of 2400 MHz. The RTX 5090 Mobile has a base clock of 990 MHz and a boost clock of 1515 MHz. The Arc B370’s higher boost clock partially compensates for its smaller core count, but the sheer difference in execution resources overwhelms any clock advantage. The RTX 5090 Mobile’s memory clock is 1750 MHz with 28 Gbps effective speed, while the Arc B370’s memory clock is listed as system shared, meaning it depends on the host system.

Both GPUs support the same API feature set: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RTX 5090 Mobile uses a PCIe 5.0 x16 bus interface, while the Arc B370 uses an IGP interface, meaning it communicates over the processor’s internal fabric rather than a dedicated PCIe link. Both have display outputs listed as portable device dependent, and both use no power connectors. The RTX 5090 Mobile’s predecessor is the GeForce 40 Mobile series, while the Arc B370 has no recorded predecessor or successor.

FAQ

Q: How much faster is the RTX 5090 Mobile than the Arc B370 in 3DMark Steel Nomad DX12?

A: The RTX 5090 Mobile scores 5871 points, while the Arc B370 scores 1184 points. The Arc B370 trails by -79.8 percent, meaning the RTX 5090 Mobile delivers roughly five times the score.

Q: What is the percentile ranking of each GPU?

A: The Arc B370 sits at the 5th percentile of all GPUs, while the RTX 5090 Mobile sits at the 84th percentile.

Q: How much memory does each GPU have?

A: The RTX 5090 Mobile has 24 GB of GDDR7 memory on a 256-bit bus with 896.0 GB/s bandwidth. The Arc B370 uses system-shared memory, with bus width and bandwidth listed as system shared or system dependent.

Q: What are the TDP values for each GPU?

A: The Arc B370 has a TDP of 25 W. The RTX 5090 Mobile has a TDP of 95 W.

Q: Which GPU has more shading units?

A: The RTX 5090 Mobile has 10496 shading units, compared to 1280 for the Arc B370.

Q: Do both GPUs support the same APIs?

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

The Verdict

The data points to a complete performance hierarchy. The RTX 5090 Mobile is the only choice for any workload that demands high frame rates, heavy compute, or large memory buffers. Its 3DMark Steel Nomad score is nearly five times higher than the Arc B370’s, its FP32 throughput is 31.80 TFLOPS versus 6.144 TFLOPS, and its dedicated 24 GB GDDR7 memory with 896.0 GB/s bandwidth provides a consistent memory subsystem that the Arc B370 cannot match. The RTX 5090 Mobile’s 84th percentile ranking and its proximity to desktop-class rivals like the RTX 4070 Ti confirm that it is a high-end part.

The Arc B370 is a different kind of product. Its 25 W TDP, 3 nm process node, and integrated design make it suited for systems where low power draw is the priority. Its 5th percentile ranking and its position alongside GPUs like the ATI Mobility Radeon HD 5570 indicate that it is not intended for demanding 3D workloads. For basic graphics output, media playback, and light productivity, its 1280 shading units and 6.144 TFLOPS may be adequate, but the database contains no benchmarks to confirm that. The only recorded test shows it far behind the RTX 5090 Mobile.

The choice between these two comes down to the system design goals. A portable device with a 25 W integrated GPU and system-shared memory will prioritize battery life and compactness. A portable device with a 95 W discrete GPU and 24 GB of dedicated GDDR7 memory will prioritize performance at the cost of size and power. The data does not address price, availability, or real-world thermals, but the performance gap is unambiguous. The RTX 5090 Mobile wins every recorded benchmark comparison, and the Arc B370’s only advantages are its lower TDP and its more recent 3 nm manufacturing process.

Specification Differences

| Specification | Intel Arc B370 | NVIDIA GeForce RTX 5090 Mobile |

| --- | --- | --- |

| Architecture | Xe3-LPG | Blackwell 2.0 |

| Process Node | 3 nm | 5 nm |

| Foundry | Intel | TSMC |

| Transistors | unknown | 45,600 million |

| Die Size | unknown | 378 mm² |

| Transistor Density | null | 120.6M / mm² |

| Base Clock | 300 MHz | 990 MHz |

| Boost Clock | 2400 MHz | 1515 MHz |

| Memory Size | System Shared | 24 GB |

| Memory Type | System Shared | GDDR7 |

| Memory Bus Width | System Shared | 256 bit |

| Memory Bandwidth | System Dependent | 896.0 GB/s |

| Memory Clock | System Shared | 1750 MHz 28 Gbps effective |

| Shading Units | 1280 | 10496 |

| TMUs | 40 | 328 |

| ROPs | 20 | 112 |

| RT Cores | 10 | 82 |

| Tensor Cores | null | 328 |

| Pixel Rate | 48.00 GPixel/s | 169.7 GPixel/s |

| Texture Rate | 96.00 GTexel/s | 496.9 GTexel/s |

| FP32 | 6.144 TFLOPS | 31.80 TFLOPS |

| FP16 | 12.29 TFLOPS (2:1) | 31.80 TFLOPS (1:1) |

| TDP | 25 W | 95 W |

| Bus Interface | IGP | PCIe 5.0 x16 |

| Release Date | 2026-01-26 | 2025-03-26 |

| Predecessor | null | GeForce 40 Mobile |

| 3DMark Steel Nomad DX12 | 1184 | 5871 |

| Percentile vs All GPUs | 5 | 84 |

The release dates show the Arc B370 is newer, appearing on 2026-01-26 versus 2025-03-26 for the RTX 5090 Mobile, but the newer part does not outperform the older one. The RTX 5090 Mobile’s larger die, higher transistor count, dedicated memory, and broader execution resources all contribute to its dominant position. The Arc B370’s integrated nature and lower power draw define its role, but the recorded data provides no evidence that it can compete with the RTX 5090 Mobile in any performance metric.