Intel Arc Pro B60 Dual vs NVIDIA Rubin GPU Comparison

Intel Arc Pro B60 Dual and NVIDIA Rubin GPU occupy entirely different segments of the hardware landscape. The database records the Arc Pro B60 Dual as a workstation-oriented graphics card with a 50th percentile rank among all GPUs, while the Rubin GPU is a server compute module with the same 50th percentile rank. Neither part has recorded benchmark scores in the database, so the analysis relies on the full specification sheets and architectural data available.

The Arc Pro B60 Dual is built for visual computing, with display outputs, a dual-slot cooling solution, and a 400 W power envelope. The Rubin GPU is a compute accelerator with no display outputs, an SXM module form factor, and a 2300 W power envelope. The data shows two distinct products: one for rendering and graphics workstations, the other for high-throughput server workloads.

Where Each One Wins

The Intel Arc Pro B60 Dual wins in every scenario that requires a physical display connection. It ships with 4x mini-DisplayPort 2.1 outputs, which the Rubin GPU lacks entirely. Any workload that produces frames for a monitor, whether for CAD, video editing, or visualization, depends on the Arc Pro B60 Dual by default. The Rubin GPU has no outputs, meaning it cannot drive a display without additional hardware.

The Arc Pro B60 Dual also wins in pixel processing throughput. Its pixel rate is 192.0 GPixel/s, compared to 54.41 GPixel/s for the Rubin GPU. This is a 3.5x advantage in raw rasterization throughput, which directly benefits traditional graphics rendering pipelines. The Arc Pro B60 Dual has 80 ROPs versus 24 ROPs on the Rubin GPU, reinforcing its role in fill-rate-bound graphics work.

The Rubin GPU wins in raw compute throughput, memory capacity, and memory bandwidth. FP32 performance is 130.0 TFLOPS versus 12.29 TFLOPS for the Arc Pro B60 Dual, a 10.6x gap. FP16 performance is 260.0 TFLOPS versus 24.58 TFLOPS, an 10.6x gap as well. Memory bandwidth is 22.1 TB/s versus 456.0 GB/s, a 48.5x gap. Memory capacity is 288 GB versus 24 GB, a 12x gap. These are the metrics that matter for large-scale AI training, scientific simulation, and data center inference.

The Rubin GPU wins in transistor count and density. It packs 336,000 million transistors on a 1456 mm² die, while the Arc Pro B60 Dual has 19,600 million transistors on a 272 mm² die. Transistor density is 230.8M per mm² for Rubin versus 72.1M per mm² for the Arc Pro B60 Dual. The Rubin GPU is a monolithic giant built for maximum compute density.

The Rubin GPU also wins in texture processing. Its texture rate is 2,031.2 GTexel/s versus 384.0 GTexel/s for the Arc Pro B60 Dual, a 5.3x advantage. This matters for volume rendering and texture-heavy compute workloads, though the Arc Pro B60 Dual still holds the pixel rate lead.

The Verdict

The data supports a clear split. The Intel Arc Pro B60 Dual is the only choice for any task that requires a physical display output. It also holds the advantage in pixel fill rate, making it the stronger option for traditional rasterization and workstation graphics. Users who need to see their work on a monitor, connect to multiple displays, or run OpenGL or DirectX applications should select the Arc Pro B60 Dual.

The NVIDIA Rubin GPU is the choice for compute-dominated workloads that run headless. Its FP32 and FP16 throughput are an order of magnitude higher, its memory bandwidth is nearly fifty times higher, and its memory capacity is twelve times larger. Server environments, AI model training, and high-performance computing clusters that do not need display outputs will prefer the Rubin GPU. The Rubin GPU also supports PCIe 6.0 x16, while the Arc Pro B60 Dual uses PCIe 5.0 x8, which matters for data transfer rates in multi-GPU servers.

Neither product is a substitute for the other. The Arc Pro B60 Dual cannot approach the compute throughput of the Rubin GPU, and the Rubin GPU cannot output video to a display. The verdict from the database is simple: pick the Arc Pro B60 Dual for graphics workstations, pick the Rubin GPU for compute servers.

Head-to-Head Benchmarks

The database lists no head-to-head benchmark scores for these two products, and each has zero recorded wins in the comparison table. However, the specification sheet provides direct numerical comparisons that function as benchmark proxies.

The largest gap in favor of the Arc Pro B60 Dual is pixel rate. The Arc Pro B60 Dual delivers 192.0 GPixel/s, while the Rubin GPU delivers 54.41 GPixel/s. This is a 3.5x advantage for the Intel card. ROP count supports this: 80 versus 24.

The largest gap in favor of the Rubin GPU is memory bandwidth. The Rubin GPU offers 22.1 TB/s, while the Arc Pro B60 Dual offers 456.0 GB/s. This is a 48.5x difference. The Rubin GPU also has a 16384-bit memory bus versus 192-bit, and HBM4 memory versus GDDR6.

FP32 compute shows a 10.6x gap. The Rubin GPU reaches 130.0 TFLOPS, the Arc Pro B60 Dual reaches 12.29 TFLOPS. FP16 compute shows the same ratio: 260.0 TFLOPS versus 24.58 TFLOPS.

Memory capacity is 288 GB versus 24 GB, a 12x difference. The Rubin GPU also has 28672 shading units versus 2560, an 11.2x difference. TMUs are 896 versus 160, a 5.6x difference. The Rubin GPU has 896 tensor cores, while the Arc Pro B60 Dual has no tensor core count listed.

Texture rate is 2,031.2 GTexel/s versus 384.0 GTexel/s, a 5.3x advantage for the Rubin GPU.

The Arc Pro B60 Dual has a higher base clock: 2000 MHz versus 700 MHz. The boost clocks are closer: 2400 MHz versus 2267 MHz. The Arc Pro B60 Dual also has a higher memory clock in effective terms: 19 Gbps versus 10.8 Gbps, though the effective bandwidth comparison reverses due to bus width.

The Arc Pro B60 Dual is smaller in die size: 272 mm² versus 1456 mm². It is built on a 5 nm process, while the Rubin GPU uses a 3 nm process. The Arc Pro B60 Dual uses 19,600 million transistors, the Rubin GPU uses 336,000 million.

The Arc Pro B60 Dual supports DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4. The Rubin GPU lists N/A for all three APIs, confirming its server-focused role.

FAQ

Q: Which GPU has higher FP32 performance?

A: The NVIDIA Rubin GPU has 130.0 TFLOPS FP32, which is 10.6 times higher than the Intel Arc Pro B60 Dual at 12.29 TFLOPS.

Q: Can the NVIDIA Rubin GPU connect to a display?

A: No. The NVIDIA Rubin GPU has no display outputs, while the Intel Arc Pro B60 Dual has 4x mini-DisplayPort 2.1 outputs.

Q: How does memory capacity compare between the two?

A: The NVIDIA Rubin GPU has 288 GB of HBM4 memory, while the Intel Arc Pro B60 Dual has 24 GB of GDDR6 memory.

Q: Which GPU has higher pixel fill rate?

A: The Intel Arc Pro B60 Dual has a pixel rate of 192.0 GPixel/s, which is 3.5 times higher than the NVIDIA Rubin GPU at 54.41 GPixel/s.

Q: What is the memory bandwidth difference?

A: The NVIDIA Rubin GPU has 22.1 TB/s bandwidth, which is 48.5 times higher than the Intel Arc Pro B60 Dual at 456.0 GB/s.

Q: Which GPU has a larger transistor count?

A: The NVIDIA Rubin GPU has 336,000 million transistors, compared to 19,600 million for the Intel Arc Pro B60 Dual.

Architecture Differences

The Intel Arc Pro B60 Dual uses the Xe2-HPG architecture on the BMG-G21 chip, part of the Battlemage (Pro Series) generation. The NVIDIA Rubin GPU uses the Rubin architecture on the GR100 chip, part of the Server Rubin (Rxx) generation. These are separate design families with different priorities.

The Arc Pro B60 Dual has 2560 shading units, 160 TMUs, 80 ROPs, and 20 ray tracing cores. It has no tensor core count listed. The Rubin GPU has 28672 shading units, 896 TMUs, 24 ROPs, and 896 tensor cores. It has no ray tracing core count listed. The Rubin GPU allocates more silicon to compute units and tensor operations, while the Arc Pro B60 Dual balances ROPs for graphics output.

The process nodes differ. The Arc Pro B60 Dual is on a 5 nm TSMC process, the Rubin GPU is on a 3 nm TSMC process. Both use TSMC as the foundry. The Rubin GPU achieves a transistor density of 230.8M per mm², versus 72.1M per mm² for the Arc Pro B60 Dual.

Memory architecture is fundamentally different. The Arc Pro B60 Dual uses GDDR6 on a 192-bit bus, while the Rubin GPU uses HBM4 on a 16384-bit bus. The memory clock is 2375 MHz (19 Gbps effective) for the Arc Pro B60 Dual, and 2695 MHz (10.8 Gbps effective) for the Rubin GPU. The bus width difference drives the bandwidth gap.

The Rubin GPU has a predecessor listed as Server Blackwell, while the Arc Pro B60 Dual has no predecessor listed. Neither has a successor listed.

The Arc Pro B60 Dual supports DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4. The Rubin GPU lists N/A for all three, reflecting its lack of a graphics software stack.

Specification Differences

The two products differ in nearly every measured field.

Process node: 5 nm for the Arc Pro B60 Dual, 3 nm for the Rubin GPU.

Transistor count: 19,600 million versus 336,000 million.

Die size: 272 mm² versus 1456 mm².

Base clock: 2000 MHz versus 700 MHz.

Boost clock: 2400 MHz versus 2267 MHz.

Memory clock: 2375 MHz (19 Gbps effective) versus 2695 MHz (10.8 Gbps effective).

Memory size: 24 GB versus 288 GB.

Memory type: GDDR6 versus HBM4.

Memory bus width: 192 bit versus 16384 bit.

Memory bandwidth: 456.0 GB/s versus 22.1 TB/s.

Shading units: 2560 versus 28672.

TMUs: 160 versus 896.

ROPs: 80 versus 24.

Ray tracing cores: 20 for the Arc Pro B60 Dual, not listed for the Rubin GPU.

Tensor cores: not listed for the Arc Pro B60 Dual, 896 for the Rubin GPU.

Pixel rate: 192.0 GPixel/s versus 54.41 GPixel/s.

Texture rate: 384.0 GTexel/s versus 2,031.2 GTexel/s.

FP32: 12.29 TFLOPS versus 130.0 TFLOPS.

FP16: 24.58 TFLOPS versus 260.0 TFLOPS.

TDP: 400 W versus 2300 W.

Slot width: Dual-slot versus SXM Module.

Power connectors: 1x 16-pin for the Arc Pro B60 Dual, none listed for the Rubin GPU.

Suggested PSU: 800 W versus 2700 W.

Bus interface: PCIe 5.0 x8 versus PCIe 6.0 x16.

Display outputs: 4x mini-DisplayPort 2.1 versus no outputs.

APIs: DirectX 12 Ultimate, OpenGL 4.6, Vulkan 1.4 for the Arc Pro B60 Dual; N/A for all on the Rubin GPU.

Dimensions: The Arc Pro B60 Dual is 300 mm long, 110 mm high, and 40 mm wide. The Rubin GPU has no dimensions listed.

Release date: 2025-09-04 for the Arc Pro B60 Dual, 2025-12-31 for the Rubin GPU.

The Arc Pro B60 Dual has a launch MSRP of 1,199 USD. The Rubin GPU has no launch MSRP listed.

Production status is Active for both products. The Rubin GPU lists Server Blackwell as its predecessor, while the Arc Pro B60 Dual has no predecessor. Neither has a successor.