Intel Arc B390 vs NVIDIA RTX 5000 Embedded Ada Generation X2 Comparison

The database comparison for the Intel Arc B390 and the NVIDIA RTX 5000 Embedded Ada Generation X2 covers two parts with different architectures, memory schemes, and recorded benchmark histories. The Intel part is an integrated GPU in the Arc Graphics-M (Panther Lake) generation, while the NVIDIA part is in the Ada-MW generation and is listed in the GeForce 50-series. The benchmark record is one-sided: the Intel part has a measured score, and the NVIDIA part has none.

FAQ

Q: What benchmark score does the Intel Arc B390 have?

A: The recorded 3DMark Steel Nomad DX12 score is 1482, placing it in the 9th percentile of all GPUs.

Q: Does the NVIDIA RTX 5000 Embedded Ada Generation X2 have a benchmark score?

A: No. Its benchmark list is empty and its average benchmark score is 0, though the database lists it in the 50th percentile of all GPUs.

Q: How does the Intel Arc B390 compare with its nearest recorded rivals?

A: It is 1.3% above the GeForce GT 520MX (1463), 1.5% above the GeForce 800M (1460), 2.5% above the GeForce GT 625 OEM (1446), and 2.7% above the GeForce GT 710 (1443).

Q: What memory configurations are recorded for these two parts?

A: The Intel part uses System Shared memory with System Dependent bandwidth. The NVIDIA part uses 16 GB GDDR6 on a 256-bit bus with 576.0 GB/s bandwidth.

Q: What process nodes and foundries are listed?

A: Intel Arc B390 is on a 3 nm Intel process. NVIDIA RTX 5000 Embedded Ada Generation X2 is on a 5 nm TSMC process.

Q: What are the TDP values?

A: Intel Arc B390 is 80 W; the NVIDIA part is 150 W. Both are listed as IGP with no power connectors.

Architecture Differences

Intel uses the Xe3-LPG architecture on the Panther Lake chip. NVIDIA uses Ada Lovelace on the AD103 chip. Intel's process node is 3 nm at Intel; NVIDIA's is 5 nm at TSMC. Intel does not list transistor count or die size; NVIDIA lists 45,900 million transistors on a 379 mm² die, a transistor density of 121.1M / mm². The Intel part is in the Arc Graphics-M (Panther Lake) generation, while the NVIDIA part is in the Ada-MW generation and is listed in the GeForce 50-series.

Compute resources differ sharply. The NVIDIA part has 9728 shading units, 304 TMUs, 112 ROPs, 76 RT cores, and 304 tensor cores. The Intel part has 1536 shading units, 48 TMUs, 24 ROPs, 12 RT cores, and no listed tensor cores. Clock behavior also differs: Intel lists a 300 MHz base and 2500 MHz boost; NVIDIA lists a 930 MHz base and 1680 MHz boost.

Memory architecture separates the two. Intel uses System Shared memory with System Dependent bandwidth, while NVIDIA uses 16 GB GDDR6 on a 256-bit bus with 576.0 GB/s bandwidth and a memory clock of 2250 MHz, described as 18 Gbps effective. The NVIDIA part also uses a PCIe 4.0 x16 bus interface, while the Intel part uses an IGP bus interface.

Throughput figures show the NVIDIA part at 32.69 TFLOPS FP32 and 32.69 TFLOPS FP16 (1:1). The Intel part is at 7.680 TFLOPS FP32 and 15.36 TFLOPS FP16 (2:1). Pixel rate is 188.2 GPixel/s versus 60.00 GPixel/s; texture rate is 510.7 GTexel/s versus 120.0 GTexel/s. TDP is 150 W versus 80 W. Both parts are IGP, use no power connectors, and list identical API support: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Intel part was released on 2026-01-26; the NVIDIA part on 2023-03-20. The NVIDIA part lists Ampere-MW as predecessor and Blackwell-MW as successor; the Intel part lists no predecessor or successor.

Head-to-Head Benchmarks

The database records no paired head-to-head benchmark entries for this pair. The only measured result belongs to the Intel Arc B390: a 3DMark Steel Nomad DX12 score of 1482, which places it in the 9th percentile of all GPUs. The NVIDIA RTX 5000 Embedded Ada Generation X2 has no benchmark entries and an average benchmark score of 0, so no NVIDIA score is available to compare.

Intel's recorded score can be positioned against its nearest rivals, all from NVIDIA: the GeForce GT 520MX scores 1463, 1.3% below; the GeForce 800M scores 1460, 1.5% below; the GeForce GT 625 OEM scores 1446, 2.5% below; and the GeForce GT 710 scores 1443, 2.7% below. The Intel part's largest recorded margin over a listed rival is therefore 2.7% against the GeForce GT 710. The database lists zero paired wins for either side, and because the NVIDIA part has no measured score, no NVIDIA win margin can be derived.

The Verdict

On the recorded data, there is no benchmark winner: the Intel part has a score, and the NVIDIA part does not. The Intel Arc B390 is the only part in this pair with a measured 3DMark Steel Nomad DX12 result, and it carries an 80 W TDP. The NVIDIA RTX 5000 Embedded Ada Generation X2 is the only part with a fixed 16 GB GDDR6 memory subsystem, 576.0 GB/s bandwidth, 304 tensor cores, and a PCIe 4.0 x16 bus interface. The NVIDIA part also lists a 150 W TDP and a 50th percentile classification among all GPUs, but that classification is not accompanied by a measured average score. A user selecting strictly from the database would choose the Intel part for a verified benchmark score and lower TDP, or the NVIDIA part for the fixed memory configuration, tensor core count, and bus interface.

Specification Differences

The table below lists only fields where the two parts differ.

| Field | Intel Arc B390 | NVIDIA RTX 5000 Embedded Ada Generation X2 |

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

| Manufacturer | Intel | NVIDIA |

| Chip | Panther Lake | AD103 |

| Architecture | Xe3-LPG | Ada Lovelace |

| Process node | 3 nm | 5 nm |

| Foundry | Intel | TSMC |

| Transistors | unknown | 45,900 million |

| Die size | unknown | 379 mm² |

| Transistor density | Not listed | 121.1M / mm² |

| Series | Not listed | GeForce 50-series |

| Generation | Arc Graphics-M (Panther Lake) | Ada-MW |

| Base clock | 300 MHz | 930 MHz |

| Boost clock | 2500 MHz | 1680 MHz |

| Memory clock | System Shared | 2250 MHz (18 Gbps effective) |

| Memory size | System Shared | 16 GB |

| Memory type | System Shared | GDDR6 |

| Memory bus width | System Shared | 256 bit |

| Memory bandwidth | System Dependent | 576.0 GB/s |

| Shading units | 1536 | 9728 |

| TMUs | 48 | 304 |

| ROPs | 24 | 112 |

| RT cores | 12 | 76 |

| Tensor cores | Not listed | 304 |

| Pixel rate | 60.00 GPixel/s | 188.2 GPixel/s |

| Texture rate | 120.0 GTexel/s | 510.7 GTexel/s |

| FP32 | 7.680 TFLOPS | 32.69 TFLOPS |

| FP16 | 15.36 TFLOPS (2:1) | 32.69 TFLOPS (1:1) |

| TDP | 80 W | 150 W |

| Bus interface | IGP | PCIe 4.0 x16 |

| Release date | 2026-01-26 | 2023-03-20 |

| Predecessor | Not listed | Ampere-MW |

| Successor | Not listed | Blackwell-MW |

| Benchmark entries | 3DMark Steel Nomad DX12 score recorded | No benchmark entries |

| Average benchmark score | 1482 | 0 |

| Percentile vs all GPUs | 9 | 50 |

| Nearest rivals | GeForce GT 520MX, GeForce 800M, GeForce GT 625 OEM, GeForce GT 710 | None listed |