Intel Arc Pro A60 vs NVIDIA Rubin GPU Comparison

The Verdict

The database records show two fundamentally different products. The Intel Arc Pro A60 is a professional workstation GPU with measured benchmark results, while the NVIDIA Rubin GPU is a server-class compute module with no recorded benchmark scores. The Arc Pro A60 sits at the 88th percentile of all GPUs in the database, with an average benchmark score of 60,326. The Rubin GPU holds the 50th percentile position, but this is based on zero recorded measurements, making its average score 0. Any selection between these two must be driven by workload type: the Arc Pro A60 is the only one with verified performance data for OpenCL and Vulkan tasks, while the Rubin GPU offers a vastly larger memory pool and compute throughput on paper, intended for server deployment where benchmark scores in this database are not yet populated. For anyone needing a working display-capable GPU with measured results, the Arc Pro A60 is the only option. For server-side acceleration with enormous memory capacity, the Rubin GPU is the target hardware, but its performance cannot be quantified from the current data.

Architecture Differences

The Intel Arc Pro A60 uses the DG2-256 chip built on TSMC's 6 nm process, housing 11,500 million transistors on a 269 mm² die with a transistor density of 42.8 million per mm². It belongs to the Alchemist generation of Intel's Xe-HPG architecture, designed for professional graphics. The NVIDIA Rubin GPU uses the GR100 chip fabricated on TSMC's 3 nm node, packing 336,000 million transistors across a 1456 mm² die, achieving a density of 230.8 million per mm². This places the Rubin in NVIDIA's Server Rubin generation, a successor to Server Blackwell.

Clock behavior differs significantly. The Arc Pro A60 has a base clock of 900 MHz and a boost of 2050 MHz, with memory running at 2000 MHz or 16 Gbps effective. The Rubin GPU starts at a lower 700 MHz base but boosts to 2267 MHz, with memory at 2695 MHz or 10.8 Gbps effective. The Rubin's much higher boost relative to its base suggests a design tuned for burst workloads.

Memory architectures are entirely different classes. The Arc Pro A60 carries 12 GB of GDDR6 on a 192-bit bus, yielding 384.0 GB/s of bandwidth. The Rubin GPU features 288 GB of HBM4 on a 16384-bit bus, delivering 22.1 TB/s, which is roughly 57 times the bandwidth of the Arc Pro A60. The Rubin also has a far larger shading unit count at 28,672 versus 2,048 for the Arc, and 896 tensor cores dedicated to AI workloads, a feature the Arc lacks entirely.

The Rubin GPU has no display outputs, while the Arc Pro A60 provides four DisplayPort 2.0 connections. The Rubin uses an SXM module form factor with a PCIe 6.0 x16 interface, whereas the Arc is a single-slot card with PCIe 4.0 x16. API support also diverges: the Arc supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, while the Rubin lists N/A for all three, reinforcing its server-only positioning.

FAQ

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

A: The Intel Arc Pro A60 has an average benchmark score of 60,326, derived from two recorded tests. The NVIDIA Rubin GPU has no benchmark scores recorded, so its average is 0.

Q: What is the transistor count difference between the two?

A: The NVIDIA Rubin GPU contains 336,000 million transistors on a 1456 mm² die, while the Intel Arc Pro A60 contains 11,500 million transistors on a 269 mm² die. The Rubin has roughly 29 times the transistor count.

Q: How does memory bandwidth compare?

A: The Arc Pro A60 provides 384.0 GB/s from 12 GB of GDDR6 on a 192-bit bus. The Rubin GPU provides 22.1 TB/s from 288 GB of HBM4 on a 16384-bit bus, which is about 57 times higher bandwidth.

Q: Can the NVIDIA Rubin GPU output to displays?

A: No, the Rubin GPU lists no display outputs. The Intel Arc Pro A60 has four DisplayPort 2.0 outputs.

Q: What is the power requirement for each?

A: The Arc Pro A60 has a TDP of 130 W with a suggested PSU of 300 W. The Rubin GPU has a TDP of 2300 W and a suggested PSU of 2700 W.

Q: Which GPU supports DirectX 12 Ultimate?

A: The Intel Arc Pro A60 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The NVIDIA Rubin GPU lists N/A for DirectX, OpenGL, and Vulkan.

Specification Differences

The two GPUs differ in nearly every measured specification. The Arc Pro A60 uses a 6 nm process, while the Rubin uses 3 nm. Transistor counts are 11,500 million versus 336,000 million, and die sizes are 269 mm² versus 1456 mm². Transistor density is 42.8M per mm² for the Arc, versus 230.8M per mm² for the Rubin.

Clock speeds: base 900 MHz versus 700 MHz, boost 2050 MHz versus 2267 MHz. Memory clock is 2000 MHz (16 Gbps effective) for the Arc, versus 2695 MHz (10.8 Gbps effective) for the Rubin.

Memory specifications: 12 GB GDDR6 on a 192-bit bus with 384.0 GB/s bandwidth for the Arc; 288 GB HBM4 on a 16384-bit bus with 22.1 TB/s for the Rubin.

Compute units: the Arc has 2,048 shading units, 128 TMUs, 64 ROPs, and 16 RT cores, with no tensor cores. The Rubin has 28,672 shading units, 896 TMUs, 24 ROPs, and 896 tensor cores, with no listed RT cores.

Pixel and texture rates: the Arc delivers 131.2 GPixel/s and 262.4 GTexel/s, while the Rubin delivers 54.41 GPixel/s and 2,031.2 GTexel/s. FP32 performance is 8.397 TFLOPS for the Arc versus 130.0 TFLOPS for the Rubin. FP16 is 16.79 TFLOPS (2:1) for the Arc versus 260.0 TFLOPS (2:1) for the Rubin.

Power and form factor: the Arc is a single-slot card with a 130 W TDP and a 300 W suggested PSU, using PCIe 4.0 x16. The Rubin is an SXM module with a 2300 W TDP and a 2700 W suggested PSU, using PCIe 6.0 x16.

Display outputs: the Arc has four DisplayPort 2.0 outputs; the Rubin has none. The Arc supports DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4; the Rubin lists N/A for all three APIs. Release dates differ: the Arc launched on 2023-06-05, while the Rubin is dated 2025-12-31.

Head-to-Head Benchmarks

The head-to-head benchmark section is empty in the database, with no recorded tests comparing the two directly. However, the Arc Pro A60 has two individual benchmark scores: Geekbench OpenCL at 63,485 and Geekbench Vulkan at 57,166. These produce an average of 60,326. The Rubin GPU has no benchmark entries at all, so no direct comparison can be made from measured data.

The Arc Pro A60's nearest rivals in the database provide context for its standing. Its average score of 60,326 puts it essentially on par with the NVIDIA GeForce RTX 4090, which averages 60,347, a delta of 0 percent. It sits 0.3 percent ahead of the AMD Radeon Pro Vega 48 at 60,140. It trails the AMD Radeon Pro W6600M by 2.5 percent, which scores 61,896, and it leads the AMD Radeon PRO V710 by 2.8 percent, which scores 58,657. These deltas show the Arc Pro A60 clustering tightly with high-end consumer and professional GPUs in the database's measurements.

The Rubin GPU has no nearest rivals listed and no average score, so its standing cannot be evaluated through the same lens. Its raw specification data indicates far higher FP32 compute, memory capacity, and bandwidth than the Arc, but without benchmark scores, the database cannot confirm how that translates to real-world performance.

Where Each One Wins

The Intel Arc Pro A60 wins in every category where measured data exists. It has a recorded average benchmark score of 60,326, placing it at the 88th percentile of all GPUs. It delivers verified Geekbench OpenCL and Vulkan results, supports modern graphics APIs including DirectX 12 Ultimate and Vulkan 1.4, and provides four DisplayPort 2.0 outputs for professional display workloads. Its 130 W TDP and 300 W suggested PSU make it deployable in standard workstation slots, and its single-slot design fits conventional chassis. For any task requiring rendering, display output, or API-level graphics compatibility, the Arc Pro A60 is the functional choice.

The NVIDIA Rubin GPU wins on raw hardware specifications. Its 130.0 TFLOPS of FP32 is roughly 15 times the Arc's 8.397 TFLOPS. Its 288 GB of HBM4 memory dwarfs the Arc's 12 GB, and its 22.1 TB/s bandwidth is orders of magnitude higher. The 896 tensor cores provide dedicated AI acceleration that the Arc lacks entirely. The 3 nm process with 230.8M transistors per mm² gives it a density advantage, and the PCIe 6.0 x16 interface offers a faster bus. The Rubin also has a much higher boost clock at 2267 MHz versus 2050 MHz for the Arc.

The use-case split follows directly from these differences. The Arc Pro A60 suits professional graphics workstations: it has display outputs, graphics API support, and measured performance in compute and Vulkan workloads. Its modest 130 W power draw allows deployment in standard systems. The Rubin GPU targets server environments where raw compute, massive memory capacity, and tensor core throughput matter more than graphics output or API compatibility. Its 2300 W TDP and SXM module form factor demand dedicated server infrastructure, and its lack of display outputs confirms it is not intended for interactive graphics. The database cannot rank the Rubin against the Arc in benchmarks because no measurements exist, but the specification gap in compute and memory is clear. For anyone choosing between the two, the decision rests on whether the workload requires verified graphics performance (Arc) or maximum server-side compute resources (Rubin).