Intel Arc Pro A60 vs NVIDIA GeForce RTX 5090 Comparison

Where Each One Wins

The recorded data tells a remarkably one-sided story, with the NVIDIA GeForce RTX 5090 winning both head-to-head benchmark comparisons against the Intel Arc Pro A60. The database shows two wins for NVIDIA and zero for Intel across the shared test suite. That said, the Intel Arc Pro A60 still holds its own in a different sense: it occupies a distinct market position with a much lower power envelope and a professional-oriented feature set that makes it suitable for specific workstation tasks where raw compute throughput is not the primary concern.

The RTX 5090 dominates in raw computational workloads. Its Geekbench OpenCL score of 334,370 versus Intel's 63,485 represents a 426.7% advantage, a staggering margin that places the NVIDIA card in an entirely different performance tier. Similarly, the Vulkan test shows the RTX 5090 scoring 376,728 against Intel's 57,166, a 559% lead. These are not incremental differences; they are generational gaps that separate enthusiast-class hardware from professional entry-level offerings.

However, the Intel Arc Pro A60 wins in practical deployment scenarios. It is a single-slot card with a 130 W TDP and a 300 W suggested PSU, making it far easier to integrate into dense workstation environments where space and power are constrained. The RTX 5090 demands a 575 W TDP and a 950 W suggested PSU, which fundamentally changes system design requirements. For users who prioritize physical footprint and thermal management over absolute performance, the Intel card offers a compelling trade-off.

Architecture Differences

The architectural divide between these two GPUs is substantial. NVIDIA's RTX 5090 uses the GB202 chip built on the Blackwell 2.0 architecture, fabricated on a 5 nm process at TSMC. It packs 92,200 million transistors onto a 750 mm² die, yielding a transistor density of 122.9 million per square millimeter. The Intel Arc Pro A60, by contrast, uses the DG2-256 chip with Xe-HPG architecture, built on a 6 nm process, containing 11,500 million transistors on a 269 mm² die with a density of 42.8 million per square millimeter.

The memory subsystems could not be more different. The RTX 5090 carries 32 GB of GDDR7 memory across a 512-bit bus, delivering 1.79 TB/s of bandwidth. The Arc Pro A60 has 12 GB of GDDR6 on a 192-bit bus, achieving 384.0 GB/s. That is a 4.7x bandwidth advantage for NVIDIA, which directly translates into its massive compute lead.

Compute resources also diverge sharply. The RTX 5090 features 21,760 shading units, 680 texture mapping units, 176 ROPs, 170 ray tracing cores, and 680 tensor cores. Intel's card offers 2,048 shading units, 128 TMUs, 64 ROPs, and 16 ray tracing cores, with no tensor cores listed. The FP32 throughput figures tell the story: 104.8 TFLOPS for NVIDIA versus 8.397 TFLOPS for Intel. Even the FP16 numbers differ in approach, with NVIDIA achieving 104.8 TFLOPS at a 1:1 ratio while Intel reaches 16.79 TFLOPS at a 2:1 ratio.

Both cards support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API compatibility is identical. However, the RTX 5090 offers PCIe 5.0 x16 connectivity while the Arc Pro A60 uses PCIe 4.0 x16. Display outputs also differ: NVIDIA provides one HDMI 2.1b port and three DisplayPort 2.1b connections, while Intel offers four DisplayPort 2.0 outputs.

Head-to-Head Benchmarks

The database contains exactly two head-to-head benchmark comparisons, and both are decisive NVIDIA victories. In Geekbench OpenCL, the RTX 5090 scores 334,370 against Intel's 63,485. The delta percentage of 426.7% means NVIDIA outperforms Intel by more than four times in this compute-oriented workload. This test typically stresses raw shader throughput and memory bandwidth, both areas where the RTX 5090's specifications suggest overwhelming superiority.

The Geekbench Vulkan result is even more lopsided. NVIDIA scores 376,728 versus Intel's 57,166, a 559% delta. Vulkan workloads often benefit from efficient driver overhead and parallel task submission, and the RTX 5090's massive shading unit count and higher clock speeds appear to compound its advantage in this API. The boost clock difference is notable: 2,407 MHz for NVIDIA versus 2,050 MHz for Intel, though the base clocks differ more dramatically at 2,017 MHz versus 900 MHz.

These benchmark results align with the architectural disparity. The RTX 5090's 1.79 TB/s memory bandwidth allows it to feed its 21,760 shading units without bottleneck, while the Arc Pro A60's 384.0 GB/s bandwidth constrains its 2,048 shading units. Pixel rate figures reinforce this: 423.6 GPixel/s for NVIDIA versus 131.2 GPixel/s for Intel, and texture rates of 1,636.8 GTexel/s versus 262.4 GTexel/s.

Interestingly, the average benchmark score comparison shows a different picture than the head-to-head tests. The RTX 5090 averages 79,842 across all recorded benchmarks with a 92nd percentile ranking among all GPUs. The Arc Pro A60 averages 60,326 with an 88th percentile ranking. The percentile gap of four points is much narrower than the raw score gap, suggesting that Intel's card still outperforms a large portion of the GPU market even if it cannot compete with NVIDIA's flagship.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The NVIDIA GeForce RTX 5090 has an average benchmark score of 79,842, while the Intel Arc Pro A60 averages 60,326. The RTX 5090 also ranks in the 92nd percentile among all GPUs compared to Intel's 88th percentile.

Q: How much faster is the RTX 5090 in Geekbench OpenCL?

A: The RTX 5090 scores 334,370 versus the Arc Pro A60's 63,485, a 426.7% advantage. This means NVIDIA delivers more than five times the OpenCL performance of Intel's card.

Q: What is the memory configuration difference?

A: The RTX 5090 uses 32 GB of GDDR7 memory on a 512-bit bus with 1.79 TB/s bandwidth. The Arc Pro A60 uses 12 GB of GDDR6 on a 192-bit bus with 384.0 GB/s bandwidth.

Q: Do both GPUs support the same DirectX version?

A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. API compatibility is identical despite the significant performance differences.

Q: What are the power requirements for each card?

A: The RTX 5090 has a 575 W TDP and requires a 950 W suggested PSU. The Arc Pro A60 has a 130 W TDP and requires a 300 W suggested PSU. The Intel card also uses a single-slot design while NVIDIA uses dual-slot.

Q: What is the market positioning based on percentile rankings?

A: The RTX 5090 sits in the 92nd percentile of all GPUs, while the Arc Pro A60 sits in the 88th percentile. Despite the massive performance gap in direct comparison, both cards outperform the majority of GPUs in the database.

The Verdict

The data makes one conclusion unavoidable: the NVIDIA GeForce RTX 5090 is in a completely different performance class than the Intel Arc Pro A60. In every recorded head-to-head benchmark, NVIDIA wins by margins exceeding 400%. The 559% Vulkan advantage and 426.7% OpenCL advantage are not merely incremental improvements; they represent fundamentally different tiers of computational capability. Anyone selecting a GPU for maximum compute throughput should choose the RTX 5090 without hesitation.

However, the Intel Arc Pro A60 has its own logic. Its 130 W TDP versus NVIDIA's 575 W means dramatically lower power consumption. Its single-slot design versus NVIDIA's dual-slot form factor enables denser system configurations. The 300 W suggested PSU versus 950 W allows integration into existing workstation platforms without power supply upgrades. For professional environments that prioritize these physical constraints, the Arc Pro A60 offers a rational choice, especially given its 88th percentile ranking indicates it still outperforms most GPUs in the database.

The RTX 5090 also offers more memory at 32 GB versus 12 GB, which matters for large datasets and high-resolution textures. Its GDDR7 memory type and 512-bit bus provide bandwidth that Intel cannot approach. The 170 ray tracing cores versus 16 suggest NVIDIA will handle ray-traced workloads far more effectively, and the 680 tensor cores versus none indicate AI acceleration capabilities that Intel's card lacks entirely.

The release timeline also matters. The RTX 5090 launched on January 29, 2025, while the Arc Pro A60 launched on June 5, 2023. That 20-month gap explains some of the technological disparity, with NVIDIA's newer Blackwell 2.0 architecture benefiting from two generations of development over Intel's Xe-HPG.

For users who need maximum performance, the RTX 5090 is the only choice. For users who need a compact, efficient professional GPU that handles standard workloads competently, the Arc Pro A60 remains viable. The database does not record any benchmark where Intel wins, so performance-oriented buyers should disregard the Arc Pro A60 entirely.

Specification Differences

The two GPUs differ across nearly every specification category. The RTX 5090 uses a 5 nm process versus Intel's 6 nm, and NVIDIA's die size of 750 mm² dwarfs Intel's 269 mm². Transistor counts follow suit: 92,200 million versus 11,500 million, with density at 122.9M per mm² versus 42.8M per mm².

Clock speeds show NVIDIA running at 2,017 MHz base and 2,407 MHz boost, while Intel operates at 900 MHz base and 2,050 MHz boost. Memory clocks differ as well: 1,750 MHz with 28 Gbps effective for NVIDIA versus 2,000 MHz with 16 Gbps effective for Intel. The RTX 5090's 32 GB GDDR7 configuration on a 512-bit bus contrasts with Intel's 12 GB GDDR6 on a 192-bit bus, producing bandwidth of 1.79 TB/s versus 384.0 GB/s.

Shader resources favor NVIDIA massively: 21,760 versus 2,048 shading units, 680 versus 128 TMUs, 176 versus 64 ROPs, 170 versus 16 ray tracing cores, and 680 tensor cores versus none. Pixel rate stands at 423.6 GPixel/s versus 131.2 GPixel/s, and texture rate at 1,636.8 GTexel/s versus 262.4 GTexel/s. FP32 compute reaches 104.8 TFLOPS versus 8.397 TFLOPS, while FP16 shows 104.8 TFLOPS at 1:1 ratio versus 16.79 TFLOPS at 2:1 ratio.

Power and physical specifications also diverge. NVIDIA draws 575 W with a 950 W suggested PSU, uses a dual-slot design and one 16-pin connector. Intel draws 130 W with a 300 W suggested PSU, uses a single-slot design and lists no power connectors. The RTX 5090 measures 304 mm in length, 137 mm in height, and 40 mm in width, while Intel's dimensions are not recorded. Bus interfaces separate them too: PCIe 5.0 x16 versus PCIe 4.0 x16, and display outputs differ between NVIDIA's HDMI 2.1b plus three DisplayPort 2.1b versus Intel's four DisplayPort 2.0 connections.