Intel Arc Pro B65 vs Intel Iris Xe Graphics 80EU Mobile Comparison

FAQ

Q: What are the core architecture differences between the Intel Arc Pro B65 and the Intel Iris Xe Graphics 80EU Mobile?

A: The Arc Pro B65 uses the Xe2-HPG architecture on a 5 nm TSMC process with the BMG-G21 chip, while the Iris Xe uses Generation 12.2 on a 10 nm Intel process with the Raptor Lake chip. The Arc Pro B65 belongs to the Battlemage (Pro Series) generation, whereas the Iris Xe is part of HD Graphics-M (Raptor Lake).

Q: How do the memory subsystems compare?

A: The Arc Pro B65 has 32 GB of GDDR6 memory on a 256-bit bus with 608.0 GB/s bandwidth. The Iris Xe uses System Shared memory with a System Shared bus width and System Dependent bandwidth, meaning it relies on the host system's RAM.

Q: What are the raw compute differences in FP32 performance?

A: The Arc Pro B65 delivers 12.29 TFLOPS of FP32 compute, while the Iris Xe provides 1.856 TFLOPS. This makes the Arc Pro B65 approximately 6.6 times faster in single-precision floating-point throughput.

Q: What is the power requirement difference?

A: The Arc Pro B65 has a 200 W TDP with a suggested 550 W PSU and a 1x 8-pin power connector. The Iris Xe has a 15 W TDP and is an IGP with no separate power connectors, drawing power directly from the portable device's motherboard.

Q: What display outputs are available?

A: The Arc Pro B65 offers 4x DisplayPort 2.1 outputs. The Iris Xe's display outputs are listed as Portable Device Dependent, meaning they vary based on the laptop or portable device it is integrated into.

Q: Which API levels do the two GPUs support?

A: The Arc Pro B65 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Iris Xe supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The Arc Pro B65 has a higher DirectX feature level.

Where Each One Wins

The Intel Arc Pro B65 is the clear winner in every measured category where the two can be compared directly. It wins on compute throughput, memory bandwidth, pixel and texture rates, and API feature support. The Iris Xe Graphics 80EU Mobile wins only in power efficiency, with a 15 W TDP versus 200 W, and in its integration into portable devices where no discrete card is needed.

For workloads that demand sustained rendering, large data sets, or high-resolution output, the Arc Pro B65 is the only viable option. The Iris Xe is suitable for basic display output, light productivity, and scenarios where the system must operate within a 15 W power envelope. The Arc Pro B65's 32 GB GDDR6 frame buffer allows it to handle large scenes and multi-display configurations, while the Iris Xe's shared memory model ties its performance to system RAM speed and capacity.

The Arc Pro B65 also wins on interface flexibility with PCIe 5.0 x16, while the Iris Xe uses a Ring Bus interface. This gives the discrete card a much wider data path for CPU-GPU communication, especially relevant for professional workloads that stream large geometry or texture data.

Architecture Differences

The Arc Pro B65 is built on the Xe2-HPG architecture, a high-performance graphics design aimed at discrete professional cards. It uses the BMG-G21 chip manufactured on a 5 nm process at TSMC, with 19,600 million transistors packed into a 272 mm² die, yielding a transistor density of 72.1M per mm². This is a modern, dense design optimized for raw throughput.

The Iris Xe Graphics 80EU Mobile uses the Generation 12.2 architecture on the Raptor Lake chip, fabricated on Intel's 10 nm process. No transistor count, die size, or density figures are recorded in the database for this part. It is an integrated GPU designed to share system resources and operate within a tight thermal envelope.

The Arc Pro B65 includes 20 ray tracing cores, a feature absent from the Iris Xe's specifications. It also has 2,560 shading units, 160 texture mapping units, and 80 ROPs. The Iris Xe has 640 shading units, 40 TMUs, and 20 ROPs. Both support DirectX 12 and Vulkan 1.4, but the Arc Pro B65 reaches DirectX 12 Ultimate (12_2), which includes features like ray tracing and mesh shaders, while the Iris Xe tops out at DirectX 12 (12_1).

The Arc Pro B65 uses GDDR6 memory with a dedicated 256-bit bus, while the Iris Xe uses System Shared memory, making its bandwidth dependent on the host platform. The Arc Pro B65 also has a fixed base and boost clock of 2400 MHz, whereas the Iris Xe runs at a 300 MHz base and boosts to 1450 MHz.

Specification Differences

| Specification | Intel Arc Pro B65 | Intel Iris Xe Graphics 80EU Mobile |

|---|---|---|

| Architecture | Xe2-HPG | Generation 12.2 |

| Process Node | 5 nm | 10 nm |

| Foundry | TSMC | Intel |

| Transistors | 19,600 million | Not recorded |

| Die Size | 272 mm² | Not recorded |

| Transistor Density | 72.1M / mm² | Not recorded |

| Base Clock | 2400 MHz | 300 MHz |

| Boost Clock | 2400 MHz | 1450 MHz |

| Memory Size | 32 GB | System Shared |

| Memory Type | GDDR6 | System Shared |

| Memory Bus Width | 256 bit | System Shared |

| Memory Bandwidth | 608.0 GB/s | System Dependent |

| Shading Units | 2560 | 640 |

| TMUs | 160 | 40 |

| ROPs | 80 | 20 |

| Ray Tracing Cores | 20 | None |

| Pixel Rate | 192.0 GPixel/s | 29.00 GPixel/s |

| Texture Rate | 384.0 GTexel/s | 58.00 GTexel/s |

| FP32 Performance | 12.29 TFLOPS | 1.856 TFLOPS |

| FP16 Performance | 24.58 TFLOPS (2:1) | 3.712 TFLOPS (2:1) |

| TDP | 200 W | 15 W |

| Slot Width | Dual-slot | IGP |

| Power Connectors | 1x 8-pin | None |

| Suggested PSU | 550 W | None |

| Bus Interface | PCIe 5.0 x16 | Ring Bus |

| Display Outputs | 4x DisplayPort 2.1 | Portable Device Dependent |

| DirectX Support | 12 Ultimate (12_2) | 12 (12_1) |

| Release Date | 2026-03-31 | 2023-01-03 |

Head-to-Head Benchmarks

The recorded benchmark data shows no direct head-to-head scores between these two GPUs. However, the specification differences are large enough to make the performance gap clear from the compute and memory figures alone.

The Arc Pro B65 delivers 12.29 TFLOPS of FP32 compute, which is 6.6 times the Iris Xe's 1.856 TFLOPS. In FP16, the Arc Pro B65 reaches 24.58 TFLOPS versus 3.712 TFLOPS, a 6.6 times advantage as well. This means any shader-heavy workload, from rendering to compute-based physics, will run substantially faster on the discrete card.

Pixel throughput favors the Arc Pro B65 at 192.0 GPixel/s, compared to 29.00 GPixel/s on the Iris Xe. That is a 6.6 times difference in fill rate, which directly impacts resolution scaling and framebuffer operations. Texture rate follows the same pattern: 384.0 GTexel/s versus 58.00 GTexel/s, again a 6.6 times gap. These ratios are consistent because they scale directly with the shading unit count, which is 2,560 versus 640.

Memory bandwidth is where the gap becomes even more pronounced. The Arc Pro B65 has 608.0 GB/s of dedicated GDDR6 bandwidth, while the Iris Xe's bandwidth is System Dependent, meaning it shares the system memory bus with the CPU. In practice, shared memory bandwidth is typically far below dedicated GDDR6, and it is also subject to contention from other system components.

The Arc Pro B65 also has 20 ray tracing cores, which the Iris Xe lacks entirely. Any workload using ray tracing will simply not run on the Iris Xe at hardware-accelerated speeds. The DirectX 12 Ultimate (12_2) feature level on the Arc Pro B65 enables additional rendering features over the Iris Xe's DirectX 12 (12_1) support.

Clock behavior differs significantly as well. The Arc Pro B65 runs at a fixed 2400 MHz for both base and boost, with no clock fluctuation noted. The Iris Xe runs at 300 MHz base and boosts to 1450 MHz, but as an integrated part, its sustained clocks depend on the laptop's thermal and power management.

The Verdict

The Intel Arc Pro B65 is a discrete professional GPU designed for workloads that require high compute throughput, large memory capacity, and advanced graphics features. Its 32 GB GDDR6 frame buffer, 608.0 GB/s bandwidth, and 12.29 TFLOPS of FP32 performance position it for tasks like large-scene rendering, multi-display output, and compute-heavy applications. The 20 ray tracing cores and DirectX 12 Ultimate support add modern rendering capabilities that the Iris Xe cannot match.

The Iris Xe Graphics 80EU Mobile is an integrated solution for portable devices. Its 15 W TDP makes it suitable for thin-and-light laptops where power draw and heat are constrained. The 640 shading units and 1.856 TFLOPS of FP32 compute are sufficient for basic desktop composition, video playback, and light 2D or casual 3D workloads. It uses system memory, so its performance is tied to the host platform's RAM speed and capacity.

The data shows no scenario where the Iris Xe outperforms the Arc Pro B65 in raw graphics throughput. The Arc Pro B65 is faster in every recorded compute, pixel, texture, and memory metric. The only advantage the Iris Xe holds is its power consumption and its integration into portable devices, eliminating the need for a separate graphics card.

For a stationary workstation or desktop professional setup, the Arc Pro B65 is the appropriate choice. For a portable device where battery life and thermal limits are the primary constraints, the Iris Xe is the only option that fits. The Arc Pro B65's 200 W TDP requires a 550 W PSU and a dual-slot footprint, while the Iris Xe has no such requirements.

The release dates also indicate different lifecycles. The Iris Xe shipped in January 2023 and has a successor listed as Arc Graphics-M. The Arc Pro B65 was released in March 2026 and remains active in production. Both are currently active, but the Arc Pro B65 represents a newer generation of Intel graphics technology.