Intel Arc Graphics 2 Xe Mobile vs NVIDIA GeForce RTX 5090 Comparison

Where Each One Wins

The recorded data places these two graphics parts at opposite ends of the performance spectrum. The Intel Arc Graphics 2 Xe Mobile sits at the 50th percentile among all GPUs in the database, while the NVIDIA GeForce RTX 5090 ranks at the 92nd percentile. That 42-point percentile gap translates into a categorical difference in workload capability. The Intel part is an integrated graphics processor designed for mobile systems, with a 25 W TDP and shared system memory. The RTX 5090 is a dual-slot discrete add-in board with a 575 W TDP and dedicated GDDR7 memory. Every benchmark category where both parts have recorded scores shows the NVIDIA product ahead, often by orders of magnitude.

The Intel Arc Graphics 2 Xe Mobile has no individual benchmark entries in the database, meaning its aggregate score is zero and it holds no recorded wins in any test. The RTX 5090, by contrast, carries ten recorded benchmark scores spanning DirectX 9 through DirectX 12, OpenCL, Vulkan, 2D, 3D, and compute workloads. In terms of use-case fit, the Intel part targets lightweight, power-constrained portable devices where integrated graphics suffice for basic display output and low-demand applications. The RTX 5090 addresses high-end desktop rendering, GPU compute, and intensive 3D workloads, as evidenced by its 3DMark Steel Nomad score of 18,355 and its Geekbench OpenCL score of 334,370.

The wins distribution is one-sided: zero wins for the Intel integrated part, zero recorded benchmark scores, and ten benchmark entries for the NVIDIA part. The functional split is therefore not about which part wins a given test, but about which workloads each part is physically and architecturally equipped to handle. The RTX 5090 delivers 104.8 TFLOPS of FP32 throughput and 1.79 TB/s of memory bandwidth; the Intel part delivers 1,280.0 GFLOPS of FP32 and system-dependent bandwidth. Any task that scales with raw compute throughput, memory bandwidth, or rasterization rate belongs to the NVIDIA side. Tasks that require minimal power draw and no discrete power connectors belong to the Intel side.

Architecture Differences

The two GPUs come from different foundries and different design philosophies. The Intel Arc Graphics 2 Xe Mobile uses the Wildcat Lake chip built on Intel's 3 nm process node with the Xe3-LPG architecture, belonging to the Arc Graphics-M generation. The NVIDIA GeForce RTX 5090 uses the GB202 chip built on TSMC's 5 nm node with the Blackwell 2.0 architecture, part of the GeForce 50 series. The transistor counts differ drastically: the RTX 5090 packs 92,200 million transistors on a 750 mm² die with a density of 122.9M per mm², while the Intel part's transistor count and die size are listed as unknown in the database.

Compute resource counts reveal the scale gap. The Intel part has 256 shading units, 16 texture mapping units, 8 ROPs, and 2 ray tracing cores. The RTX 5090 has 21,760 shading units, 680 TMUs, 176 ROPs, 170 RT cores, and 680 tensor cores. The Intel part lists no tensor core count in the database. The shading unit ratio is 85 to 1 in favor of NVIDIA. The TMU ratio is 42.5 to 1. The ROP ratio is 22 to 1. The RT core ratio is 85 to 1. These structural differences drive the pixel rate and texture rate gaps: the RTX 5090 reaches 423.6 GPixel/s and 1,636.8 GTexel/s, while the Intel part manages 20.00 GPixel/s and 40.00 GTexel/s.

Clock behavior also differs. The Intel part has a 300 MHz base clock and a 2500 MHz boost clock. The RTX 5090 runs at a 2017 MHz base and 2407 MHz boost, with memory clocked at 1750 MHz for 28 Gbps effective. The Intel part's boost clock is actually 93 MHz higher than NVIDIA's, but that advantage is meaningless given the 85-fold difference in shading units. Memory architecture is fundamentally different: the Intel part uses system shared memory with a system-dependent bus width and bandwidth, while the RTX 5090 uses 32 GB of GDDR7 across a 512-bit bus for 1.79 TB/s. The API support is identical: both list DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Head-to-Head Benchmarks

The RTX 5090 has ten recorded benchmark scores; the Intel Arc Graphics 2 Xe Mobile has none. The database therefore contains no direct head-to-head benchmark entries between these two parts. However, the RTX 5090's individual scores can be interpreted against its nearest rivals to establish its performance tier. In 3DMark Steel Nomad DX12, the RTX 5090 scores 18,355. In Geekbench OpenCL, it scores 334,370. In Geekbench Vulkan, it scores 376,728. PassMark results show 226 in DirectX 10, 341 in DirectX 11, 185 in DirectX 12, 395 in DirectX 9, 1,413 in G2D, 39,650 in G3D, and 26,756 in GPU compute.

The average benchmark score for the RTX 5090 is 79,842, placing it ahead of the NVIDIA Tesla P100 PCIe 16 GB by 0.3%, ahead of the Tesla P100 PCIe 12 GB by 0.6%, and ahead of the AMD Radeon RX 6850M XT by 1.1%. It trails the AMD Radeon Pro Vega 64X by 1.4%. These deltas are small, indicating that the RTX 5090 sits in a tightly packed cluster at the top of the database's scoring distribution. The nearest rival score range spans from 78,940 to 80,959, a spread of just 2,019 points, while the RTX 5090's own average sits at 79,842, almost exactly in the middle of that band.

The Intel part's 50th percentile ranking and zero average score place it far outside this cluster. Because the Intel part has no benchmark entries, there are no exact score deltas to report against the RTX 5090. The data simply shows an absence of recorded performance data for the Intel integrated GPU, while the RTX 5090 delivers scores that rank among the top 8% of all GPUs tracked in the database. The PassMark G3D score of 39,650 and the Geekbench Vulkan score of 376,728 represent the strongest recorded results for the NVIDIA part in their respective test families.

Specification Differences

The two parts differ in nearly every recorded specification field. The Intel Arc Graphics 2 Xe Mobile uses the Wildcat Lake chip on a 3 nm Intel process, while the RTX 5090 uses the GB202 chip on a 5 nm TSMC process. The RTX 5090 lists 92,200 million transistors and a 750 mm² die; the Intel part lists both as unknown. Transistor density for the RTX 5090 is 122.9M per mm²; no density is recorded for the Intel part. The Intel part has a 300 MHz base clock and 2500 MHz boost; the RTX 5090 has a 2017 MHz base and 2407 MHz boost. Memory configuration differs completely: the Intel part uses system shared memory, while the RTX 5090 uses 32 GB of GDDR7 on a 512-bit bus with 1.79 TB/s bandwidth. The Intel part's memory clock is listed as system shared.

Compute unit counts differ across every category. The Intel part has 256 shading units, 16 TMUs, 8 ROPs, and 2 RT cores. The RTX 5090 has 21,760 shading units, 680 TMUs, 176 ROPs, 170 RT cores, and 680 tensor cores. Pixel rate is 20.00 GPixel/s for Intel versus 423.6 GPixel/s for NVIDIA. Texture rate is 40.00 GTexel/s versus 1,636.8 GTexel/s. FP32 throughput is 1,280.0 GFLOPS versus 104.8 TFLOPS. FP16 throughput is 2.560 TFLOPS at a 2:1 ratio for Intel versus 104.8 TFLOPS at a 1:1 ratio for NVIDIA. The TDP is 25 W for Intel versus 575 W for NVIDIA. The Intel part is an IGP with no power connectors; the RTX 5090 is dual-slot with a single 16-pin connector and a suggested 950 W PSU. The bus interface is IGP for Intel versus PCIe 5.0 x16 for NVIDIA.

Physical dimensions are recorded only for the RTX 5090: 304 mm length, 137 mm height, and 40 mm width. Display outputs differ: the Intel part lists portable device dependent outputs, while the RTX 5090 lists one HDMI 2.1b and three DisplayPort 2.1b outputs. Release dates differ by over a year: the RTX 5090 launched on 2025-01-29, and the Intel part launched on 2026-04-15. The RTX 5090 has a launch MSRP of 1,999 USD; the Intel part has no recorded launch MSRP. The predecessors differ: the Intel part succeeds HD Graphics-M, and the RTX 5090 succeeds GeForce 40. The RTX 5090 lists GeForce 60 as its successor; the Intel part lists no successor.

FAQ

Q: Which GPU has the higher percentile ranking in the database?

A: The NVIDIA GeForce RTX 5090 ranks at the 92nd percentile among all GPUs, while the Intel Arc Graphics 2 Xe Mobile ranks at the 50th percentile.

Q: How many benchmark scores does each GPU have recorded?

A: The Intel Arc Graphics 2 Xe Mobile has no benchmark entries and an average benchmark score of zero. The RTX 5090 has ten recorded scores across 3DMark, Geekbench OpenCL, Geekbench Vulkan, and multiple PassMark tests.

Q: What are the closest rivals to the RTX 5090 based on average score?

A: The nearest rivals are the NVIDIA Tesla P100 PCIe 16 GB with a 0.3% lower score, the NVIDIA Tesla P100 PCIe 12 GB with a 0.6% lower score, the AMD Radeon RX 6850M XT with a 1.1% lower score, and the AMD Radeon Pro Vega 64X with a 1.4% higher score.

Q: How do the FP32 compute rates compare?

A: The RTX 5090 delivers 104.8 TFLOPS of FP32 throughput, while the Intel Arc Graphics 2 Xe Mobile delivers 1,280.0 GFLOPS, a difference of roughly 82 times in favor of NVIDIA.

Q: What memory configurations do the two GPUs use?

A: The Intel Arc Graphics 2 Xe Mobile uses system shared memory with system-dependent bandwidth and bus width. The RTX 5090 uses 32 GB of GDDR7 on a 512-bit bus with 1.79 TB/s of bandwidth.

Q: What are the power requirements for each GPU?

A: The Intel Arc Graphics 2 Xe Mobile has a 25 W TDP, is an integrated processor with no power connectors, and no suggested PSU. The RTX 5090 has a 575 W TDP, uses a single 16-pin power connector, and has a suggested PSU of 950 W.