Intel Arc A380E vs NVIDIA GeForce RTX 5070 Mobile Comparison

Where Each One Wins

The recorded data shows a starkly uneven contest. The NVIDIA GeForce RTX 5070 Mobile holds every benchmark win in the database, with the Intel Arc A380E carrying no recorded benchmark scores of its own. The RTX 5070 Mobile’s average benchmark score of 29,928 places it in the 75th percentile of all GPUs, while the Arc A380E sits at the 50th percentile. This means the Intel part lands exactly at the median of the database, whereas the NVIDIA part outperforms roughly three-quarters of all recorded GPUs.

The RTX 5070 Mobile’s wins are comprehensive across API generations and workload types. In Geekbench’s OpenCL test, it scores 122,238, and in Vulkan it scores 116,960. These are compute-heavy workloads that show the NVIDIA part’s raw throughput advantage. In Passmark’s DirectX tests, it wins across the board: DirectX 9 at 214, DirectX 10 at 129, DirectX 11 at 192, and DirectX 12 at 93. The Passmark G3D score of 20,355 and GPU compute score of 8,279 further confirm its dominance in both rasterization and general-purpose compute.

The Arc A380E has no recorded wins because it has no recorded benchmarks in the database. This is not a close contest; it is a one-sided comparison. The use-case split is therefore simple: for any task measured by the database, the RTX 5070 Mobile is the only option with data showing performance. The Arc A380E’s lack of scores means it cannot be positioned as a competitor in any measured workload.

Architecture Differences

The two GPUs come from completely different design philosophies and process generations. Intel’s Arc A380E uses the DG2-128 chip built on the Xe-HPG architecture, part of the Alchemist (Arc 3) generation. NVIDIA’s RTX 5070 Mobile uses the GB206 chip on the Blackwell 2.0 architecture, part of the GeForce 50 Mobile generation.

The manufacturing process differs significantly. Intel uses a 6 nm TSMC process, while NVIDIA uses a 5 nm TSMC process. This process advantage shows in transistor density: the NVIDIA chip packs 121.0 million transistors per mm², versus Intel’s 45.9 million per mm². The RTX 5070 Mobile’s GB206 die is 181 mm² and holds 21,900 million transistors, while the Arc A380E’s DG2-128 die is 157 mm² with 7,200 million transistors. The NVIDIA chip fits roughly three times the transistors into a slightly larger die.

Core counts tell a similar story. The RTX 5070 Mobile has 4,608 shading units, 144 texture mapping units, 48 ROPs, 36 ray tracing cores, and 144 tensor cores. The Arc A380E has 1,024 shading units, 64 TMUs, 32 ROPs, and 8 ray tracing cores, with no tensor cores listed. The NVIDIA part has 4.5 times the shading units and 4.5 times the ray tracing cores.

Memory architecture also differs completely. The RTX 5070 Mobile uses 8 GB of GDDR7 on a 128-bit bus, delivering 384.0 GB/s of bandwidth. The Arc A380E uses 6 GB of GDDR6 on a 96-bit bus, delivering 186.0 GB/s. The NVIDIA part has more than double the memory bandwidth. Its memory clock is 1500 MHz, 24 Gbps effective, versus Intel’s 1937 MHz, 15.5 Gbps effective.

The bus interface differs as well: NVIDIA uses PCIe 5.0 x16, while Intel uses PCIe 4.0 x8. The power envelope is unusual here: the RTX 5070 Mobile has a TDP of 50 W, which is lower than the Arc A380E’s 75 W. The NVIDIA part is classified as an IGP (integrated GPU) with no power connectors and no suggested PSU, while the Arc A380E is a single-slot card requiring a 250 W suggested PSU.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce RTX 5070 Mobile has an average benchmark score of 29,928. The Intel Arc A380E has no recorded average benchmark score in the database.

Q: How does the RTX 5070 Mobile compare to its nearest rivals?

A: The RTX 5070 Mobile sits within 1.7% of its nearest rivals. It is 0.1% behind the RTX 3070 Ti (29,945), 0.5% ahead of the RTX 2080 Ti (29,783), 0.6% behind the RX 6800 (30,095), and 1.7% behind the RX 6700 (30,433).

Q: What is the difference in memory bandwidth between the two?

A: The RTX 5070 Mobile delivers 384.0 GB/s from 8 GB of GDDR7 on a 128-bit bus. The Arc A380E delivers 186.0 GB/s from 6 GB of GDDR6 on a 96-bit bus.

Q: Which GPU has a lower TDP?

A: The RTX 5070 Mobile has a TDP of 50 W, which is lower than the Arc A380E’s 75 W. The NVIDIA part is listed as an IGP with no power connectors, while the Intel part is a single-slot card.

Q: Are there any benchmark tests where the Arc A380E wins?

A: No. The database records zero benchmark scores for the Arc A380E. All nine recorded benchmark scores belong to the RTX 5070 Mobile.

Q: What are the process node sizes for each GPU?

A: The Arc A380E uses a 6 nm TSMC process, while the RTX 5070 Mobile uses a 5 nm TSMC process.

Specification Differences

The two GPUs differ in nearly every measurable specification. The RTX 5070 Mobile has a larger transistor count (21,900 million versus 7,200 million), a larger die (181 mm² versus 157 mm²), and a much higher transistor density (121.0M / mm² versus 45.9M / mm²). The process node is 5 nm versus 6 nm.

Core configurations differ sharply. The RTX 5070 Mobile has 4,608 shading units versus 1,024, 144 TMUs versus 64, 48 ROPs versus 32, 36 RT cores versus 8, and 144 tensor cores versus none listed for the Intel part. The NVIDIA part’s FP32 throughput is 13.13 TFLOPS versus 4.096 TFLOPS, and its FP16 throughput is 13.13 TFLOPS (1:1) versus 8.192 TFLOPS (2:1). Pixel rate is 68.40 GPixel/s versus 64.00 GPixel/s, and texture rate is 205.2 GTexel/s versus 128.0 GTexel/s.

Memory differs in size, type, bus width, and bandwidth: 8 GB GDDR7 on a 128-bit bus at 384.0 GB/s versus 6 GB GDDR6 on a 96-bit bus at 186.0 GB/s. The memory clock is 1500 MHz (24 Gbps effective) versus 1937 MHz (15.5 Gbps effective). The bus interface is PCIe 5.0 x16 versus PCIe 4.0 x8.

Clocks are also different. The Arc A380E has a base and boost clock of 2000 MHz, while the RTX 5070 Mobile has a base of 907 MHz and a boost of 1425 MHz. The TDP is 75 W versus 50 W. The slot width is single-slot versus IGP. The Intel card has 4x DisplayPort 2.0 outputs and dimensions of 254 mm length, 127 mm height, and 20 mm width; the NVIDIA part has no listed dimensions and its display outputs are listed as portable device dependent.

The Intel part is end-of-life, released 2024-03-31, with a predecessor of Xe Graphics and a successor of Battlemage. The NVIDIA part is active, released 2025-04-14, with a predecessor of GeForce 40 Mobile and no successor listed.

Head-to-Head Benchmarks

The database contains nine benchmark scores for the RTX 5070 Mobile and none for the Arc A380E, making every head-to-head comparison a default win for the NVIDIA part. The largest single score is Geekbench OpenCL at 122,238, which represents compute performance under the OpenCL API. The Vulkan score of 116,960 is nearly as high, showing strong cross-API compute capability.

In Passmark’s suite, the G3D score of 20,355 is the highest rasterization score, followed by GPU compute at 8,279. The DirectX scores are lower in absolute terms: DirectX 9 at 214, DirectX 11 at 192, DirectX 10 at 129, and DirectX 12 at 93. The G2D score of 896 rounds out the set.

The RTX 5070 Mobile’s nearest rival data provides context for these numbers. Its average score of 29,928 is essentially tied with the RTX 3070 Ti (29,945, a 0.1% deficit) and the RTX 2080 Ti (29,783, a 0.5% lead). It trails the RX 6800 (30,095) by 0.6% and the RX 6700 (30,433) by 1.7%. This places the mobile part in the same performance class as previous flagship desktop GPUs, despite its 50 W TDP.

For the Arc A380E, there are no scores to interpret. The percentile rank of 50 indicates it sits at the median of the database, but without a benchmark score, this rank cannot be tied to any specific workload performance. The wins count is 0 for each side, though the RTX 5070 Mobile’s nine recorded scores make its dominance clear.

The Verdict

The data points to a single conclusion: the NVIDIA GeForce RTX 5070 Mobile is the only GPU of the two with measurable performance in the database. Its average score of 29,928 places it at the 75th percentile, and its nearest rivals are all previous-generation desktop flagships within a 1.7% margin. The RTX 5070 Mobile delivers this performance at a 50 W TDP, which is 25 W lower than the Arc A380E’s 75 W TDP.

The Intel Arc A380E presents a different profile entirely. It has no benchmark scores, no recorded wins, and sits at the 50th percentile. Its specifications show a smaller chip, fewer cores, slower memory, and an older process node. It is end-of-life, while the RTX 5070 Mobile is active. The Intel card does have a higher clock speed (2000 MHz versus 1425 MHz boost) and a larger physical footprint with four DisplayPort outputs, which suits a desktop add-in card use case.

From the recorded data alone, the choice is unambiguous for any compute or graphics workload: the RTX 5070 Mobile outperforms the Arc A380E across every measured category. The NVIDIA part has more shading units, more ray tracing cores, more tensor cores, higher memory bandwidth, and a smaller power draw. It also has a 5 nm process advantage and a PCIe 5.0 x16 interface versus PCIe 4.0 x8.

The Arc A380E’s only advantages are its higher base and boost clocks, its desktop form factor with specified dimensions and display outputs, and its 6 GB of GDDR6 memory, which is smaller than the RTX 5070 Mobile’s 8 GB. None of these advantages translate into a recorded benchmark win. For a user prioritizing measured performance, the RTX 5070 Mobile is the only supported choice in this comparison. For a user needing a specific desktop slot card with multiple DisplayPort outputs, the Arc A380E has a defined physical profile, but its performance remains unverified in the database.