Intel Arc A380E x2 vs NVIDIA GeForce RTX 5090 Comparison

Head-to-Head Benchmarks

The benchmark database contains recorded scores for the NVIDIA GeForce RTX 5090 across ten tests, while the Intel Arc A380E x2 has no benchmark entries in the database. This makes a direct head-to-head comparison one-sided, but the RTX 5090’s results can still be interpreted against its nearest rivals to establish a performance baseline.

The RTX 5090’s strongest showing comes in Geekbench Vulkan, where it records a score of 376,728. In Geekbench OpenCL, it posts 334,370. The Passmark G3D suite returns 39,650, while Passmark GPU Compute delivers 26,756. Legacy DirectX tests show 395 in DirectX 9, 341 in DirectX 11, 226 in DirectX 10, and 185 in DirectX 12. The 2D graphics score is 1,413, and the 3DMark Steel Nomad DX12 test produces 18,355.

With an average benchmark score of 79,842, the RTX 5090 sits at the 92nd percentile among all GPUs in the database. Its nearest rival, the NVIDIA Tesla P100 PCIe 16 GB, averages 79,605, which is 0.3% lower. The Tesla P100 PCIe 12 GB averages 79,396, a 0.6% deficit. The AMD Radeon RX 6850M XT averages 78,940, trailing by 1.1%. On the other side, the AMD Radeon Pro Vega 64X averages 80,959, which is 1.4% ahead of the RTX 5090. These delta percentages place the RTX 5090 in a tight cluster, with the largest recorded gap among its nearest rivals being just 1.4%.

The Intel Arc A380E x2, by contrast, has no benchmark scores recorded in the database. Its percentileVsAllGpus field is 50, but that figure lacks supporting test data. The absence of benchmarks means the database cannot quantify any win for the Arc A380E x2 in any workload. The win count stands at zero for both products in the head-to-head comparison, but that reflects missing data rather than parity.

The RTX 5090’s compute-oriented results are particularly notable. Passmark GPU Compute at 26,756 is roughly two-thirds of the G3D score, which suggests strong general-purpose throughput. The Geekbench Vulkan score exceeds the OpenCL score by about 12.7%, indicating the architecture responds well to Vulkan’s explicit control model. The 3DMark Steel Nomad DX12 score of 18,355 is a modern workload result, and it aligns with the card’s DirectX 12 Ultimate feature set.

Architecture Differences

The two GPUs come from different architectural families and process nodes. The Intel Arc A380E x2 uses the DG2-128 chip built on Xe-HPG architecture, specifically from the Alchemist (Arc 3) generation. It is fabricated on a 6 nm process at TSMC, with 7,200 million transistors on a 157 mm² die. That works out to a transistor density of 45.9 million per square millimeter.

The NVIDIA GeForce RTX 5090 uses the GB202 chip on Blackwell 2.0 architecture, part of the GeForce 50 series. It is built on a 5 nm process, also at TSMC, with 92,200 million transistors on a 750 mm² die. The transistor density is 122.9 million per square millimeter, which is more than 2.6 times denser than the Intel part.

Core counts differ dramatically. The Arc A380E x2 has 1,024 shading units, 64 texture mapping units, and 32 ROPs. It also includes 8 ray tracing cores. The RTX 5090 has 21,760 shading units, 680 TMUs, and 176 ROPs, plus 170 ray tracing cores and 680 tensor cores. The NVIDIA part has no tensor core counterpart in the Intel specification, as the Arc A380E x2 lists none.

Clock behavior also separates them. The Arc A380E x2 runs at a fixed 2000 MHz for both base and boost, with memory at 1937 MHz (15.5 Gbps effective). The RTX 5090 has a base clock of 2017 MHz and a boost of 2407 MHz, with memory at 1750 MHz (28 Gbps effective). The RTX 5090’s boost clock is 407 MHz higher than its base, while the Intel card does not deviate from its 2000 MHz figure.

Memory configurations are far apart. The Arc A380E x2 uses 6 GB of GDDR6 on a 96-bit bus, delivering 186.0 GB/s of bandwidth. The RTX 5090 uses 32 GB of GDDR7 on a 512-bit bus, delivering 1.79 TB/s. That is roughly 9.6 times the bandwidth, though the database does not provide a direct comparison metric.

Pixel and texture rates reflect the core count differences. The Arc A380E x2 outputs 64.00 GPixel/s and 128.0 GTexel/s. The RTX 5090 outputs 423.6 GPixel/s and 1,636.8 GTexel/s. FP32 compute is 4.096 TFLOPS for the Intel part and 104.8 TFLOPS for the NVIDIA part. FP16 on the Arc card is 8.192 TFLOPS at a 2:1 ratio, while the RTX 5090 achieves 104.8 TFLOPS at a 1:1 ratio.

Power and physical specs differ as well. The Arc A380E x2 has a TDP of 130 W, uses a single 6-pin power connector, and requires a 300 W suggested PSU. It is a single-slot card. The RTX 5090 has a TDP of 575 W, uses a 16-pin connector, and requires a 950 W suggested PSU. It is a dual-slot card. The Intel card measures 265 mm in length, 127 mm in height, and 20 mm in width. The RTX 5090 measures 304 mm in length, 137 mm in height, and 40 mm in width.

Both support PCIe, but at different revisions and widths. The Arc A380E x2 uses PCIe 4.0 x8, while the RTX 5090 uses PCIe 5.0 x16. Display outputs also differ: the Intel card has 8x mini-DisplayPort 2.0, while the NVIDIA card has 1x HDMI 2.1b and 3x DisplayPort 2.1b. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Where Each One Wins

The recorded data shows the RTX 5090 wins in every benchmark category where scores exist. Its 92nd percentile ranking among all GPUs indicates top-tier placement. The only rival that beats it in the nearest rivals list is the AMD Radeon Pro Vega 64X, by 1.4%, which is a narrow margin. The RTX 5090 beats the Tesla P100 PCIe 16 GB by 0.3%, the Tesla P100 PCIe 12 GB by 0.6%, and the AMD Radeon RX 6850M XT by 1.1%.

For the Intel Arc A380E x2, the database has no benchmark scores, so no workload can be identified where it wins against the RTX 5090. Its specifications suggest it is positioned for a different market segment. The Arc A380E x2 has 8 display outputs, which is more than the RTX 5090’s 4 outputs, and it is a single-slot card with a 130 W TDP. Those characteristics point toward multi-display or compact deployment scenarios, but the database does not contain test results to confirm performance in those roles.

The RTX 5090’s 32 GB of GDDR7 memory and 512-bit bus make it suited for large memory footprint workloads, such as high-resolution rendering or large dataset compute. The Arc A380E x2’s 6 GB of GDDR6 on a 96-bit bus is a much smaller memory pool. The FP32 compute gap is substantial: 104.8 TFLOPS versus 4.096 TFLOPS, a 25.6 times difference. The texture rate gap is similarly large, with the RTX 5090 delivering 1,636.8 GTexel/s against 128.0 GTexel/s.

The ray tracing core counts also favor the RTX 5090 by a wide margin, 170 versus 8. The tensor cores present only on the RTX 5090, at 680, provide AI acceleration that the Intel part lacks entirely. For any compute or graphics workload recorded in the database, the RTX 5090 is the clear winner. The Arc A380E x2 remains an unquantified entry.

FAQ

Q: What is the average benchmark score of the NVIDIA GeForce RTX 5090?

A: The RTX 5090 has an average benchmark score of 79,842, placing it at the 92nd percentile among all GPUs in the database.

Q: How does the RTX 5090 compare to its nearest rival, the NVIDIA Tesla P100 PCIe 16 GB?

A: The RTX 5090 averages 79,842, while the Tesla P100 PCIe 16 GB averages 79,605. That puts the RTX 5090 ahead by 0.3%.

Q: Does the Intel Arc A380E x2 have any benchmark scores in the database?

A: No, the Intel Arc A380E x2 has no recorded benchmark entries. Its percentileVsAllGpus field shows 50, but there are no test scores to support that figure.

Q: What is the process node difference between the two GPUs?

A: The Intel Arc A380E x2 uses a 6 nm TSMC process, while the NVIDIA GeForce RTX 5090 uses a 5 nm TSMC process.

Q: How much memory does each GPU have?

A: The Intel Arc A380E x2 has 6 GB of GDDR6 on a 96-bit bus with 186.0 GB/s bandwidth. The NVIDIA GeForce RTX 5090 has 32 GB of GDDR7 on a 512-bit bus with 1.79 TB/s bandwidth.

Q: What is the TDP of each card?

A: The Intel Arc A380E x2 has a TDP of 130 W, while the NVIDIA GeForce RTX 5090 has a TDP of 575 W.

Specification Differences

The two GPUs differ in nearly every specification field recorded in the database.

Architecture and chip: The Intel Arc A380E x2 uses the DG2-128 chip on Xe-HPG architecture from the Alchemist (Arc 3) generation. The NVIDIA GeForce RTX 5090 uses the GB202 chip on Blackwell 2.0 architecture from the GeForce 50 series.

Process node and foundry: Both use TSMC, but the Intel part is on 6 nm and the NVIDIA part is on 5 nm.

Transistors and die size: The Intel part has 7,200 million transistors on a 157 mm² die. The NVIDIA part has 92,200 million transistors on a 750 mm² die.

Transistor density: The Intel part has 45.9M transistors per mm². The NVIDIA part has 122.9M transistors per mm².

Clocks: The Intel part runs at 2000 MHz base and boost. The NVIDIA part runs at 2017 MHz base and 2407 MHz boost. Memory clocks are 1937 MHz (15.5 Gbps effective) for Intel and 1750 MHz (28 Gbps effective) for NVIDIA.

Memory: Intel has 6 GB GDDR6 with a 96-bit bus and 186.0 GB/s bandwidth. NVIDIA has 32 GB GDDR7 with a 512-bit bus and 1.79 TB/s bandwidth.

Core counts: Intel has 1,024 shading units, 64 TMUs, 32 ROPs, and 8 RT cores. NVIDIA has 21,760 shading units, 680 TMUs, 176 ROPs, 170 RT cores, and 680 tensor cores.

Rates: Intel outputs 64.00 GPixel/s and 128.0 GTexel/s. NVIDIA outputs 423.6 GPixel/s and 1,636.8 GTexel/s.

Compute: Intel delivers 4.096 TFLOPS FP32 and 8.192 TFLOPS FP16 (2:1). NVIDIA delivers 104.8 TFLOPS FP32 and 104.8 TFLOPS FP16 (1:1).

Power: Intel has a 130 W TDP, 1x 6-pin connector, and 300 W suggested PSU. NVIDIA has a 575 W TDP, 1x 16-pin connector, and 950 W suggested PSU.

Physical: Intel is single-slot, 265 mm long, 127 mm tall, 20 mm wide. NVIDIA is dual-slot, 304 mm long, 137 mm tall, 40 mm wide.

Bus interface: Intel uses PCIe 4.0 x8. NVIDIA uses PCIe 5.0 x16.

Display outputs: Intel has 8x mini-DisplayPort 2.0. NVIDIA has 1x HDMI 2.1b and 3x DisplayPort 2.1b.

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

Production status and release: Intel is end-of-life, released 2024-03-31. NVIDIA is active, released 2025-01-29. The NVIDIA card has a launch MSRP of 1,999 USD. The Intel card has no launch MSRP recorded.

Successor/predecessor: Intel’s predecessor is Xe Graphics and successor is Battlemage. NVIDIA’s predecessor is GeForce 40 and successor is GeForce 60.