Intel Arc A380E vs NVIDIA GeForce RTX 5090 Mobile Comparison

Head-to-Head Benchmarks

The recorded data contains no direct head-to-head benchmark results between the Intel Arc A380E and the NVIDIA GeForce RTX 5090 Mobile. The Intel Arc A380E has an empty benchmark array, meaning no scores were captured for it in the database. The RTX 5090 Mobile, however, has a full set of measurements across multiple test suites. This asymmetry makes a direct comparison of individual test scores impossible, but the available data for the RTX 5090 Mobile places it firmly in a different performance class.

The RTX 5090 Mobile achieves an average benchmark score of 45,152 across its recorded tests. Its percentile ranking of 84 means it outperforms 84 percent of all GPUs in the database. Its nearest rivals provide useful context: the AMD Radeon Pro 5500 XT scores 45,384, which is 0.5 percent higher, making the RTX 5090 Mobile essentially a statistical tie with that card. The NVIDIA GeForce RTX 4070 Ti scores 44,795, putting the RTX 5090 Mobile 0.8 percent ahead. The Intel Arc A730M scores 45,592, placing the RTX 5090 Mobile 1 percent behind that mobile GPU. Finally, the NVIDIA RTX 5880 Ada Generation scores 45,972, which is 1.8 percent higher than the RTX 5090 Mobile.

Looking at individual test scores for the RTX 5090 Mobile, the 3DMark Steel Nomad DX12 test returns 5,871. The Geekbench OpenCL score is 201,834, while the Geekbench Vulkan score is 198,405. PassMark results show a G3D score of 30,034 and a GPU compute score of 13,401. The DirectX 9 score is 324, DirectX 10 is 183, DirectX 11 is 269, and DirectX 12 is 138. The 2D graphics score is 1,057.

Because the Arc A380E has no recorded benchmark scores, the win count stands at zero for both parts. The data does not support any claim of one part beating the other in any specific test. The only quantitative comparison available is through the percentile ranks: the Arc A380E sits at the 50th percentile, while the RTX 5090 Mobile sits at the 84th percentile. That gap of 34 percentile points indicates a substantial difference in overall positioning, but without overlapping test data, the exact magnitude of the performance delta cannot be quantified from the database.

Architecture Differences

The two GPUs come from entirely different architectural lineages. The Intel Arc A380E uses the DG2-128 chip based on Xe-HPG architecture, belonging to the Alchemist generation under the Arc 3 branding. The RTX 5090 Mobile uses the GB203 chip based on Blackwell 2.0 architecture, part of the GeForce 50 Mobile generation. These are separated by an entire product generation cycle, with Intel's part being end-of-life while NVIDIA's part remains active in production.

The manufacturing process differs significantly. The Intel chip is fabricated on a 6 nm process at TSMC, while the NVIDIA chip uses a 5 nm process, also at TSMC. The transistor counts reflect the scale difference: the Intel DG2-128 packs 7,200 million transistors on a 157 mm² die, giving a transistor density of 45.9 million per square millimeter. The NVIDIA GB203 contains 45,600 million transistors on a 378 mm² die, achieving a density of 120.6 million per square millimeter. The NVIDIA chip has more than six times the transistor count and nearly 2.4 times the die area.

Clock behavior differs substantially. The Intel part runs at a flat 2,000 MHz for both base and boost clocks, with no game clock listed. The NVIDIA part has a base clock of 990 MHz and a boost clock of 1,515 MHz. Despite the lower clocks, the NVIDIA GPU delivers far higher throughput because of its massive shader count. Memory clocks also differ: the Intel card uses 1,937 MHz with 15.5 Gbps effective, while the NVIDIA card uses 1,750 MHz with 28 Gbps effective.

The compute architectures diverge in their FP16 handling. The Intel Arc A380E delivers 8.192 TFLOPS of FP16 with a 2:1 ratio relative to its FP32 throughput of 4.096 TFLOPS. The RTX 5090 Mobile delivers 31.80 TFLOPS of FP16 with a 1:1 ratio, meaning it does not gain a rate advantage by using reduced precision. The NVIDIA part also includes dedicated tensor cores, 328 of them, while the Intel part lists no tensor core count at all.

API support is identical in terms of feature level: both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The underlying hardware capabilities differ, but the exposed API surface matches.

Where Each One Wins

The data supports only one clear winner in terms of measured performance, and that is the RTX 5090 Mobile. Its 84th percentile ranking versus the Arc A380E's 50th percentile ranking indicates that the NVIDIA part sits well above the median GPU in the database, while the Intel part sits exactly at the median. The RTX 5090 Mobile's average benchmark score of 45,152, with scores ranging from 138 in PassMark DirectX 12 to 201,834 in Geekbench OpenCL, shows a broad capability across different workloads. Its nearest rivals, all scoring within roughly 2 percent of its average, confirm that it competes with desktop-class GPUs like the RTX 4070 Ti and the RTX 5880 Ada Generation.

The Intel Arc A380E has no recorded wins in any benchmark category. Its strengths must be inferred from its specifications rather than measured results. It offers a 6 GB GDDR6 memory configuration with a 96 bit bus and 186.0 GB/s bandwidth. This is suitable for lighter workloads, but nothing in the data shows it outperforming the RTX 5090 Mobile in any test.

The RTX 5090 Mobile wins in memory capacity, bandwidth, shader throughput, texture rate, and pixel rate. It has 24 GB of GDDR7 memory on a 256 bit bus with 896.0 GB/s bandwidth. Its FP32 throughput of 31.80 TFLOPS is roughly 7.8 times the Intel part's 4.096 TFLOPS. Its texture rate of 496.9 GTexel/s compares to 128.0 GTexel/s on the Intel side. Its pixel rate of 169.7 GPixel/s compares to 64.00 GPixel/s.

The use-case split, based on the recorded data, is therefore lopsided. The RTX 5090 Mobile is positioned for demanding workloads such as high-resolution gaming, compute-heavy tasks, and AI-adjacent applications that can use its tensor cores. The Intel Arc A380E, at the 50th percentile, is positioned for entry-level tasks where its 75 W power draw and single-slot form factor may be advantageous, but the database does not contain any benchmark evidence of it winning in any specific scenario.

Specification Differences

The two GPUs differ across nearly every specification field. The Intel Arc A380E uses a 6 nm process; the RTX 5090 Mobile uses 5 nm. The Intel chip has 7,200 million transistors versus 45,600 million on the NVIDIA chip. Die size is 157 mm² versus 378 mm². Transistor density is 45.9M per mm² versus 120.6M per mm².

Base clocks differ: 2,000 MHz on Intel versus 990 MHz on NVIDIA. Boost clocks also differ: 2,000 MHz versus 1,515 MHz. Memory clocks show 1,937 MHz with 15.5 Gbps effective on Intel versus 1,750 MHz with 28 Gbps effective on NVIDIA.

Memory configuration is a major split. The Intel part has 6 GB of GDDR6 on a 96 bit bus with 186.0 GB/s bandwidth. The NVIDIA part has 24 GB of GDDR7 on a 256 bit bus with 896.0 GB/s bandwidth. Memory bandwidth is nearly five times higher on the NVIDIA part.

Compute units differ: the Intel GPU has 1,024 shading units, 64 TMUs, 32 ROPs, and 8 ray tracing cores. The NVIDIA GPU has 10,496 shading units, 328 TMUs, 112 ROPs, 82 ray tracing cores, and 328 tensor cores. The Intel part lists no tensor core count.

Output rates differ: the Intel part has a pixel rate of 64.00 GPixel/s and a texture rate of 128.0 GTexel/s. The NVIDIA part has a pixel rate of 169.7 GPixel/s and a texture rate of 496.9 GTexel/s. FP32 throughput is 4.096 TFLOPS versus 31.80 TFLOPS. FP16 throughput is 8.192 TFLOPS (2:1) versus 31.80 TFLOPS (1:1).

Power and form factor differ: the Intel part has a TDP of 75 W, is single-slot, and has no power connectors. The NVIDIA part has a TDP of 95 W and is an integrated graphics processor (IGP) with no power connectors. The Intel part has a suggested PSU of 250 W; the NVIDIA part has no suggested PSU listed.

Bus interface differs: PCIe 4.0 x8 on Intel versus PCIe 5.0 x16 on NVIDIA. Display outputs differ: 4x DisplayPort 2.0 on Intel versus portable device dependent outputs on NVIDIA. Dimensions exist only for the Intel part: 254 mm length, 127 mm height, 20 mm width.

Production status differs: the Intel part is end-of-life, the NVIDIA part is active. Release dates differ: Intel in March 2024, NVIDIA in March 2025. The Intel part's predecessor is Xe Graphics and its successor is Battlemage. The NVIDIA part's predecessor is GeForce 40 Mobile and it has no listed successor.

FAQ

Q: Which GPU has a higher average benchmark score in the database?

A: The NVIDIA GeForce RTX 5090 Mobile has an average benchmark score of 45,152. The Intel Arc A380E has no recorded benchmark scores, so its average is zero.

Q: How does the RTX 5090 Mobile compare to its nearest rivals?

A: The RTX 5090 Mobile scores 0.5 percent below the AMD Radeon Pro 5500 XT, 0.8 percent above the NVIDIA GeForce RTX 4070 Ti, 1 percent below the Intel Arc A730M, and 1.8 percent below the NVIDIA RTX 5880 Ada Generation.

Q: What is the memory capacity difference between the two GPUs?

A: The Intel Arc A380E has 6 GB of GDDR6 memory on a 96 bit bus. The NVIDIA GeForce RTX 5090 Mobile has 24 GB of GDDR7 memory on a 256 bit bus. The NVIDIA part has 896.0 GB/s bandwidth versus 186.0 GB/s on the Intel part.

Q: Which GPU has a higher transistor count?

A: The NVIDIA GeForce RTX 5090 Mobile uses the GB203 chip with 45,600 million transistors. The Intel Arc A380E uses the DG2-128 chip with 7,200 million transistors.

Q: Do both GPUs support the same API levels?

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

Q: What is the production status of each GPU?

A: The Intel Arc A380E is end-of-life. The NVIDIA GeForce RTX 5090 Mobile is active.

The Verdict

The data presents a one-sided comparison. The NVIDIA GeForce RTX 5090 Mobile outperforms the Intel Arc A380E in every measurable specification that affects compute and rendering capability. Its 84th percentile ranking versus the 50th percentile ranking for the Intel part places them in different tiers entirely. The RTX 5090 Mobile's average benchmark score of 45,152, alongside its nearest rivals all scoring within 2 percent of that figure, confirms that it competes with high-end desktop GPUs rather than entry-level mobile parts.

The Intel Arc A380E offers a lower power draw of 75 W versus 95 W, a single-slot form factor, and a 250 W suggested PSU, which makes it a lighter integration burden. It also provides four DisplayPort 2.0 outputs, which is a fixed connectivity option, whereas the NVIDIA part's outputs are portable device dependent. However, the database contains no benchmark results for the Intel part, so no performance claims can be substantiated from the recorded data.

The RTX 5090 Mobile wins on memory capacity by a factor of four, bandwidth by a factor of roughly 4.8, FP32 throughput by a factor of roughly 7.8, texture rate by a factor of roughly 3.9, and pixel rate by a factor of roughly 2.7. It uses a newer process node, has more than six times the transistor count, and includes tensor cores that the Intel part lacks entirely. Its PCIe 5.0 x16 interface doubles the lane count and doubles the generation speed relative to the Intel part's PCIe 4.0 x8.

For anyone selecting between these two based on the database records, the RTX 5090 Mobile is the only part with measurable performance, and that performance places it at the 84th percentile. The Intel Arc A380E sits at the median with no recorded scores, making any performance prediction impossible from the data alone. The RTX 5090 Mobile is the clear choice for workloads that require high throughput, large memory capacity, and broad API support. The Intel part remains a low-power, compact option, but the database offers no evidence of it winning in any benchmark scenario.