Intel Arc Graphics 32EU vs NVIDIA GeForce RTX 5090 SE Comparison

Intel Arc Graphics 32EU is an integrated graphics solution built into the Arrow Lake-S processor, using the Xe-LPG architecture on a 3 nm TSMC process. The NVIDIA GeForce RTX 5090 SE is a discrete add-in board based on the GB202 chip, using the Blackwell 2.0 architecture on a 5 nm TSMC process. The database contains a single benchmark result for the Intel part, the 3DMark Steel Nomad DX12 test, where it scored 733 points. The RTX 5090 SE has no recorded benchmark scores in the database, and its average benchmark score is listed as 0. This makes a direct numerical comparison of measured performance impossible. The analysis below relies on the available data, including the Intel part’s percentile ranking, its nearest rivals, and the architectural and specification differences recorded for both products.

Head-to-Head Benchmarks

The head-to-head benchmark table is empty. There are no direct comparison scores between the Intel Arc Graphics 32EU and the NVIDIA GeForce RTX 5090 SE. The Intel part has one recorded score, 733 points in 3DMark Steel Nomad DX12. The RTX 5090 SE has no recorded scores at all, with an average benchmark score of 0. The wins counters show 0 for both products, reflecting the absence of direct test data.

The Intel Arc Graphics 32EU sits at the 3rd percentile of all GPUs in the database. Its nearest rivals provide context for this score. The Intel Arc Graphics 24EU, the Intel Arc Graphics 64EU, and the AMD Radeon HD 6470M all score 733, 733, and 723 points respectively. The NVIDIA GeForce GT 415M scores 751 points. The delta percentages show the 32EU is 0% faster than the 24EU and 64EU, 1.4% faster than the HD 6470M, and 2.4% slower than the GT 415M. This places the integrated part in the lowest performance tier of the database, roughly comparable to decade-old entry-level discrete mobile GPUs. The 3rd percentile ranking confirms that 97% of all recorded GPUs score higher.

The RTX 5090 SE holds a 50th percentile ranking among all GPUs, which is the median position. However, this percentile is computed without any benchmark data, so it does not reflect measured performance. The average benchmark score of 0 indicates no tests have been recorded. The RTX 5090 SE has no nearest rivals listed, so there are no delta percentages or comparative scores to cite. The data shows a complete lack of measurement results for the NVIDIA part.

The only meaningful benchmark comparison available is between the Intel Arc Graphics 32EU and its listed rivals. The 32EU matches the 24EU and 64EU exactly at 733 points, which indicates that within this integrated family, the number of execution units does not change the Steel Nomad result in the database. The 1.4% advantage over the Radeon HD 6470M is small, and the 2.4% deficit against the GeForce GT 415M is equally small. The recorded data suggests the 32EU performs at the very bottom of the database, with a score of 733 points.

The Verdict

The verdict must be drawn strictly from the recorded data. The Intel Arc Graphics 32EU has a measured score of 733 points in 3DMark Steel Nomad DX12, placing it at the 3rd percentile. The NVIDIA GeForce RTX 5090 SE has no measured score, an average benchmark score of 0, and no nearest rivals. No direct comparison is possible.

The Intel Arc Graphics 32EU is a 65 W integrated graphics processor with a 3 nm process node, 256 shading units, 16 TMUs, and 8 ROPs. It delivers 998.4 GFLOPS of FP32 performance and 15.60 GPixel/s of pixel rate. The RTX 5090 SE is a 500 W dual-slot discrete card with 14080 shading units, 440 TMUs, 160 ROPs, 110 ray tracing cores, and 440 tensor cores. It delivers 66.94 TFLOPS of FP32 performance and 380.3 GPixel/s of pixel rate. The raw specification differences are enormous, but the absence of benchmark data for the RTX 5090 SE prevents a measured performance verdict.

The data supports only a limited conclusion. The Intel Arc Graphics 32EU belongs to the lowest performance tier, matching the scores of the 24EU and 64EU variants and trading places with the HD 6470M and GT 415M. The RTX 5090 SE is positioned at the 50th percentile in the database, but this is not backed by any recorded score. The RTX 5090 SE has a launch MSRP of 1,499 USD, which is the only pricing information available. The database does not contain enough information to declare a winner in measured performance.

Where Each One Wins

The Intel Arc Graphics 32EU wins in the only category with recorded data: benchmark presence. It has an average benchmark score of 733, while the RTX 5090 SE has an average benchmark score of 0. In the 3DMark Steel Nomad DX12 test, the Intel part produced a score, and the RTX 5090 SE produced nothing. This is not a performance victory; it is a data availability victory.

The Intel Arc Graphics 32EU also wins on power efficiency in the database. It has a 65 W TDP, while the RTX 5090 SE has a 500 W TDP. The integrated part uses the Ring Bus interface and system shared memory, which requires no dedicated power connectors. The RTX 5090 SE requires a single 16-pin connector and a suggested PSU of 900 W. The Intel part is an IGP, meaning it occupies no expansion slot, while the RTX 5090 SE is a dual-slot card measuring 267 mm in length, 111 mm in height, and 40 mm in width.

The RTX 5090 SE wins on every raw specification category where numbers exist. It has 14080 shading units versus 256, 440 TMUs versus 16, and 160 ROPs versus 8. It has 110 ray tracing cores and 440 tensor cores, while the Intel part lists neither. Its FP32 throughput is 66.94 TFLOPS versus 998.4 GFLOPS. Its texture rate is 1,045.9 GTexel/s versus 31.20 GTexel/s. Its pixel rate is 380.3 GPixel/s versus 15.60 GPixel/s. The RTX 5090 SE has 24 GB of GDDR7 memory on a 384-bit bus with 1.34 TB/s of bandwidth, while the Intel part uses system shared memory with system dependent bandwidth.

The RTX 5090 SE also wins on clock speeds. Its base clock is 1740 MHz and boost clock is 2377 MHz, compared to 300 MHz base and 1950 MHz boost for the Intel part. The memory clock is 1750 MHz with 28 Gbps effective transfer for the NVIDIA card, while the Intel part’s memory clock is listed as system shared.

FAQ

Q: What is the average benchmark score of the Intel Arc Graphics 32EU?

A: The Intel Arc Graphics 32EU has an average benchmark score of 733 points, based on a single 3DMark Steel Nomad DX12 result.

Q: Does the NVIDIA GeForce RTX 5090 SE have any recorded benchmark scores?

A: No. The RTX 5090 SE has an empty benchmarks list and an average benchmark score of 0, with no nearest rivals recorded.

Q: How does the Intel Arc Graphics 32EU compare to its nearest rivals?

A: It matches the Intel Arc Graphics 24EU and 64EU at 733 points, is 1.4% faster than the AMD Radeon HD 6470M at 723 points, and is 2.4% slower than the NVIDIA GeForce GT 415M at 751 points.

Q: What is the percentile ranking of each product?

A: The Intel Arc Graphics 32EU is at the 3rd percentile of all GPUs, while the RTX 5090 SE is at the 50th percentile. The RTX 5090 SE ranking is not based on measured scores.

Q: How much memory does each product use?

A: The Intel Arc Graphics 32EU uses system shared memory with system dependent bandwidth. The RTX 5090 SE has 24 GB of GDDR7 memory on a 384-bit bus with 1.34 TB/s bandwidth.

Q: What are the TDP values for both products?

A: The Intel Arc Graphics 32EU has a TDP of 65 W. The RTX 5090 SE has a TDP of 500 W and requires a suggested PSU of 900 W.

Architecture Differences

The Intel Arc Graphics 32EU uses the Xe-LPG architecture, built on a 3 nm process at TSMC. The chip is Arrow Lake-S, and the generation is listed as Arc Graphics-M (Arrow Lake). The transistor count is 17,800 million on a die size of 243 mm², giving a transistor density of 73.3M per mm². The RTX 5090 SE uses the Blackwell 2.0 architecture, built on a 5 nm process at TSMC. The chip is GB202, and the generation is GeForce 50. The transistor count is 92,200 million on a die size of 750 mm², giving a transistor density of 122.9M per mm².

The Intel part has 256 shading units, 16 TMUs, and 8 ROPs. It lists no ray tracing cores and no tensor cores. The RTX 5090 SE has 14080 shading units, 440 TMUs, 160 ROPs, 110 ray tracing cores, and 440 tensor cores. The Intel part’s FP16 performance is 1.997 TFLOPS with a 2:1 ratio, while the RTX 5090 SE’s FP16 performance is 66.94 TFLOPS with a 1:1 ratio. The FP32 performance is 998.4 GFLOPS for the Intel part and 66.94 TFLOPS for the RTX 5090 SE.

The Intel part uses a Ring Bus interface and is an IGP. The RTX 5090 SE uses PCIe 5.0 x16 and is a dual-slot card. The production status is Active for both. The Intel part was released on 2024-10-23, and its predecessor is HD Graphics-M. The RTX 5090 SE was released on 2025-12-31, and its predecessor is GeForce 40, with a successor of GeForce 60. The RTX 5090 SE has a launch MSRP of 1,499 USD.

Specification Differences

The specification differences between the two products are extensive. The process node differs: 3 nm for the Intel part versus 5 nm for the NVIDIA part. The transistor count is 17,800 million versus 92,200 million. The die size is 243 mm² versus 750 mm². The transistor density is 73.3M per mm² versus 122.9M per mm².

The base clock is 300 MHz for the Intel part and 1740 MHz for the RTX 5090 SE. The boost clock is 1950 MHz versus 2377 MHz. The Intel part has no game clock listed, and its memory clock is system shared. The RTX 5090 SE has a memory clock of 1750 MHz with 28 Gbps effective transfer.

Memory configuration differs completely. The Intel part has system shared memory, system shared type, system shared bus width, and system dependent bandwidth. The RTX 5090 SE has 24 GB of GDDR7 memory, a 384-bit bus width, and 1.34 TB/s of bandwidth.

The compute units differ: 256 shading units versus 14080, 16 TMUs versus 440, and 8 ROPs versus 160. The RTX 5090 SE has 110 ray tracing cores and 440 tensor cores; the Intel part has none listed. The pixel rate is 15.60 GPixel/s versus 380.3 GPixel/s. The texture rate is 31.20 GTexel/s versus 1,045.9 GTexel/s. The FP32 throughput is 998.4 GFLOPS versus 66.94 TFLOPS. The FP16 throughput is 1.997 TFLOPS with a 2:1 ratio versus 66.94 TFLOPS with a 1:1 ratio.

The TDP is 65 W versus 500 W. The slot width is IGP versus dual-slot. The RTX 5090 SE has a 1x 16-pin power connector and a suggested PSU of 900 W; the Intel part has no power connector or suggested PSU listed. The bus interface is Ring Bus versus PCIe 5.0 x16. The display outputs are motherboard dependent for the Intel part, while the RTX 5090 SE has 1x HDMI 2.1b and 3x DisplayPort 2.1b.

The RTX 5090 SE has physical dimensions of 267 mm length, 111 mm height, and 40 mm width. The Intel part has no dimensions listed. The release dates differ: 2024-10-23 for the Intel part and 2025-12-31 for the RTX 5090 SE. The RTX 5090 SE has a launch MSRP of 1,499 USD, while the Intel part has no launch MSRP listed. The API support is identical: both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.