Intel Arc A750 vs NVIDIA RTX A5000 Mobile Comparison

The Verdict

The data separates these two clearly. The NVIDIA RTX A5000 Mobile wins 7 of the 9 head-to-head benchmarks, with particularly large margins in DirectX 10 (76.9% ahead), DirectX 11 (84.7% ahead), and Passmark G3D (25.9% ahead). Its average benchmark score is 24763, placing it at the 70th percentile of all GPUs, versus 20582 and the 66th percentile for the Intel Arc A750. If your workload leans on compute, DirectX 10/11 titles, or general 3D rendering, the RTX A5000 Mobile is the stronger pick.

The Intel Arc A750 wins only two tests: Passmark DirectX 9 (181 vs 169, a 6.6% edge) and Passmark G2D (732 vs 629, a 14.1% edge). Those wins matter for legacy DirectX 9 games and 2D desktop workloads, but they do not offset the NVIDIA card's broader dominance. The A750 also carries a launch MSRP of 289 USD, while the RTX A5000 Mobile has no listed launch price. If raw performance per the database is the priority, choose the NVIDIA. If you need the fastest 2D acceleration or play older DirectX 9 titles specifically, the Intel card has a niche.

Architecture Differences

The two GPUs come from different foundries and process nodes. The NVIDIA RTX A5000 Mobile uses the GA104 chip on Samsung's 8 nm process, packing 17,400 million transistors on a 392 mm² die, for a transistor density of 44.4M per mm². The Intel Arc A750 uses the DG2-512 chip on TSMC's 6 nm process, with 21,700 million transistors on a 406 mm² die, giving a higher density of 53.4M per mm². Intel's newer node does not translate into a performance win, as the benchmark data shows.

Architecturally, NVIDIA is on Ampere, while Intel is on Xe-HPG. The RTX A5000 Mobile has 6144 shading units, 192 TMUs, 96 ROPs, 48 RT cores, and 192 tensor cores. The Arc A750 has 3584 shading units, 224 TMUs, 112 ROPs, and 28 RT cores, but no tensor cores listed. The NVIDIA card's raw shader count is much higher, which helps in FP32 compute: 19.35 TFLOPS versus 17.20 TFLOPS. However, the Intel card doubles its FP16 rate to 34.41 TFLOPS (2:1 ratio), while NVIDIA runs FP16 at the same 19.35 TFLOPS (1:1). That asymmetry matters for mixed-precision workloads.

Memory configurations also differ. The RTX A5000 Mobile has 16 GB of GDDR6 on a 256-bit bus, delivering 448.0 GB/s. The Arc A750 has 8 GB of GDDR6 on the same 256-bit bus, but with faster effective memory at 16 Gbps, reaching 512.0 GB/s. The Intel card has higher bandwidth, but half the capacity. Both support PCIe 4.0 x16, DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Intel card has explicit display outputs (1x HDMI 2.1, 3x DisplayPort 2.0), while the NVIDIA mobile part is "Portable Device Dependent," meaning its outputs vary by laptop design.

Power delivery is another split. The RTX A5000 Mobile is rated at 150 W with no power connectors listed, typical of a mobile part. The Arc A750 is a dual-slot desktop card rated at 225 W, requiring a 1x 6-pin plus 1x 8-pin power connector and a suggested PSU of 550 W. That makes the Intel card a plug-in desktop component, while the NVIDIA card is a mobile GPU.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA RTX A5000 Mobile scores 24763 on average, versus 20582 for the Intel Arc A750. That is a difference of roughly 20% in the database's aggregate metric.

Q: Does the Intel Arc A750 win any benchmarks outright?

A: Yes. It wins Passmark DirectX 9 (181 vs 169, a 6.6% margin) and Passmark G2D (732 vs 629, a 14.1% margin). Those are the only two head-to-head tests it takes.

Q: How do the two cards compare in memory bandwidth?

A: The Intel Arc A750 has higher bandwidth at 512.0 GB/s, thanks to 16 Gbps effective memory speed, while the NVIDIA RTX A5000 Mobile delivers 448.0 GB/s from 14 Gbps effective memory. Both use 256-bit buses and GDDR6.

Q: Which GPU has more shading units?

A: The NVIDIA RTX A5000 Mobile has 6144 shading units, nearly double the 3584 shading units of the Intel Arc A750. That helps explain its FP32 throughput of 19.35 TFLOPS versus 17.20 TFLOPS.

Q: Are these cards still in production?

A: Both are listed as end-of-life. The NVIDIA RTX A5000 Mobile was released in April 2021, and the Intel Arc A750 in October 2022.

Q: What is the transistor count difference?

A: The Intel Arc A750 has 21,700 million transistors on a 406 mm² die, while the NVIDIA RTX A5000 Mobile has 17,400 million on a 392 mm² die. Intel's density is higher at 53.4M per mm² versus 44.4M per mm².

Specification Differences

| Specification | NVIDIA RTX A5000 Mobile | Intel Arc A750 |

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

| Process node | 8 nm (Samsung) | 6 nm (TSMC) |

| Transistors | 17,400 million | 21,700 million |

| Die size | 392 mm² | 406 mm² |

| Transistor density | 44.4M / mm² | 53.4M / mm² |

| Base clock | 900 MHz | 2050 MHz |

| Boost clock | 1575 MHz | 2400 MHz |

| Memory clock | 1750 MHz (14 Gbps effective) | 2000 MHz (16 Gbps effective) |

| Memory size | 16 GB | 8 GB |

| Memory bandwidth | 448.0 GB/s | 512.0 GB/s |

| Shading units | 6144 | 3584 |

| TMUs | 192 | 224 |

| ROPs | 96 | 112 |

| RT cores | 48 | 28 |

| Tensor cores | 192 | None |

| Pixel rate | 151.2 GPixel/s | 268.8 GPixel/s |

| Texture rate | 302.4 GTexel/s | 537.6 GTexel/s |

| FP32 | 19.35 TFLOPS | 17.20 TFLOPS |

| FP16 | 19.35 TFLOPS (1:1) | 34.41 TFLOPS (2:1) |

| TDP | 150 W | 225 W |

| Slot width | Not listed | Dual-slot |

| Power connectors | None | 1x 6-pin + 1x 8-pin |

| Suggested PSU | Not listed | 550 W |

| Display outputs | Portable Device Dependent | 1x HDMI 2.1, 3x DisplayPort 2.0 |

Head-to-Head Benchmarks

The biggest NVIDIA win is in Passmark DirectX 11, where it scores 133 versus 72, a 84.7% margin. That is a decisive gap for older DirectX 11 games and applications. DirectX 10 shows a similar story: 115 versus 65, a 76.9% lead. In Passmark G3D, the NVIDIA card records 15779 against 12534, a 25.9% advantage, which is the most relevant test for general 3D rendering performance. Compute workloads also favor NVIDIA: Passmark GPU Compute shows 6945 versus 5368, a 29.4% lead. Geekbench OpenCL gives NVIDIA a 12.5% edge (110877 vs 98554), while Geekbench Vulkan is closer, with NVIDIA ahead by 2.9% (88144 vs 85631). In Passmark DirectX 12, the margin narrows to just 2.9% (72 vs 70), meaning the two are nearly tied in modern DirectX 12 titles.

The Intel Arc A750's wins are smaller in relative terms. In Passmark DirectX 9, it scores 181 versus 169, a 6.6% lead. In Passmark G2D, it scores 732 versus 629, a 14.1% lead. The G2D result is the larger of the two, indicating faster 2D desktop operations. Neither win approaches the scale of NVIDIA's DirectX 10 or 11 margins. The overall win count is 7 for NVIDIA and 2 for Intel.

Where Each One Wins

The NVIDIA RTX A5000 Mobile is the clear choice for DirectX 10 and DirectX 11 workloads. Its 76.9% and 84.7% margins in those tests are the largest of any head-to-head comparison, so anyone running older game engines or legacy professional applications should favor it. It also wins the compute tests: Passmark GPU Compute by 29.4% and Geekbench OpenCL by 12.5%, making it better suited for GPGPU tasks like rendering, simulation, or machine learning inference, especially given its 192 tensor cores. Its 16 GB of memory provides twice the capacity of the Intel card, which matters for large datasets or high-resolution textures. The Geekbench Vulkan and Passmark DirectX 12 results are nearly tied, but NVIDIA still edges both by 2.9%, so there is no modern-API territory where Intel clearly wins.

The Intel Arc A750 takes the 2D desktop crown. Its Passmark G2D score of 732 versus 629, a 14.1% lead, means faster window compositing, image editing, and general desktop responsiveness. It also wins Passmark DirectX 9 by 6.6%, which is relevant for classic games from the early 2000s era. The Intel card has higher raw pixel rate (268.8 GPixel/s versus 151.2 GPixel/s) and texture rate (537.6 GTexel/s versus 302.4 GTexel/s), so in fill-rate-bound scenarios it could pull ahead, though the benchmark data does not show that in 3D tests. Its FP16 throughput of 34.41 TFLOPS is nearly double NVIDIA's 19.35 TFLOPS, so workloads that use FP16 heavily might favor Intel, but the database does not include a benchmark that isolates that. The Arc A750 also has a higher memory bandwidth of 512.0 GB/s, which helps in bandwidth-sensitive tasks, but the NVIDIA card's larger memory pool and stronger compute results dominate the overall picture.

In practical terms, the database says this: choose NVIDIA for most 3D, compute, and legacy DirectX applications. Choose Intel if you prioritize 2D speed or play DirectX 9 titles, and you are willing to accept lower scores everywhere else. The RTX A5000 Mobile is the more versatile and higher-performing part, with a 70th percentile ranking versus 66th for the Arc A750, and its aggregate score of 24763 sits 20% above the Intel card's 20582.