Intel Arc Pro B390 vs Intel Arc Pro B60 Dual Comparison

Head-to-Head Benchmarks

The recorded data contains no direct benchmark comparisons between the Intel Arc Pro B390 and the Intel Arc Pro B60 Dual. Both entries show an average benchmark score of 0 and an identical percentile rank of 50 against all GPUs in the database. Without head-to-head measurements, the comparative performance picture must be derived from the architectural specifications and compute capabilities recorded for each part.

The Intel Arc Pro B60 Dual delivers substantially higher raw compute throughput. Its FP32 performance is recorded at 12.29 TFLOPS, which is 60% above the B390's 7.680 TFLOPS. The FP16 figures follow the same pattern: the B60 Dual reaches 24.58 TFLOPS (2:1) versus 15.36 TFLOPS (2:1) for the B390. These are the largest numerical gaps in the dataset, and they indicate that the B60 Dual holds a decisive advantage in any workload that scales with shader throughput.

Pixel and texture processing show even wider disparities. The B60 Dual records a pixel rate of 192.0 GPixel/s and a texture rate of 384.0 GTexel/s. The B390 manages 60.00 GPixel/s and 120.0 GTexel/s respectively. That places the B60 Dual at 3.2 times the pixel throughput and 3.2 times the texture throughput of the B390. Rasterization-heavy tasks, such as high-resolution rendering with heavy fragment shading, would favor the B60 Dual by a wide margin.

Clock behavior adds another layer. The B60 Dual has a base clock of 2000 MHz and a boost of 2400 MHz, while the B390 operates at a 300 MHz base and a 2500 MHz boost. The B390's higher boost ceiling suggests it can reach competitive peak frequencies, but the massive gap in base clocks implies the B60 Dual maintains much higher sustained throughput under load. The B390's boost advantage of 100 MHz does little to offset the 3.2 times core-count disadvantage.

Memory architecture separates the two decisively. The B60 Dual carries 24 GB of GDDR6 on a 192-bit bus, yielding 456.0 GB/s of bandwidth. The B390 uses system-shared memory with bandwidth labeled as system dependent. In memory-bound scenarios, the B60 Dual operates with a known, dedicated bandwidth figure, while the B390 depends entirely on the host platform's memory subsystem. The B60 Dual's fixed 456.0 GB/s stands in contrast to the B390's unspecified, platform-dependent performance.

Architecture Differences

The two GPUs come from different Intel architectures and manufacturing processes. The B390 is built on the Xe3-LPG architecture using a 3 nm process at Intel's own foundry, with the Panther Lake chip. The B60 Dual uses the Xe2-HPG architecture on a 5 nm process from TSMC, based on the BMG-G21 chip. The B390 belongs to the Arc Graphics-WM (Panther Lake) generation, while the B60 Dual is part of the Battlemage (Pro Series) generation.

Transistor and die data are only available for the B60 Dual. It integrates 19,600 million transistors on a 272 mm² die, resulting in a transistor density of 72.1M per mm². The B390's transistor count and die size are listed as unknown, so no direct comparison is possible on those metrics.

Core configuration differs significantly. The B390 has 1536 shading units, 48 texture mapping units, 24 raster output units, and 12 ray tracing cores. The B60 Dual doubles or more than doubles these counts: 2560 shading units, 160 TMUs, 80 ROPs, and 20 ray tracing cores. The B60 Dual also has 4 more ray tracing cores, which could matter in ray-traced rendering workloads.

Memory specifications are fundamentally different. The B390 uses system-shared memory with an unknown bus width and system-dependent bandwidth. The B60 Dual has dedicated 24 GB GDDR6 memory on a 192-bit bus with 456.0 GB/s bandwidth. The B60 Dual's memory clock is recorded at 2375 MHz with 19 Gbps effective speed, while the B390's memory clock is listed as system shared.

Power and physical design diverge sharply. The B390 has a TDP of 80 W and is an integrated graphics processor (IGP) with no power connectors, fitting into an IGP slot width. The B60 Dual has a 400 W TDP, uses a dual-slot design, requires a single 16-pin power connector, and lists a suggested power supply of 800 W. The B60 Dual measures 300 mm in length, 110 mm in height, and 40 mm in width. The B390 has no recorded dimensions because it is an integrated part.

Interface and display outputs also differ. The B390 connects via an IGP bus interface, while the B60 Dual uses PCIe 5.0 x8. The B390's display outputs are marked as portable device dependent, whereas the B60 Dual provides 4x mini-DisplayPort 2.1 connectors. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API compatibility is identical.

Release timing places the B60 Dual first, with a release date of 2025-09-04, while the B390 followed on 2026-01-26. The B390's predecessor is listed as HD Graphics-WM, while the B60 Dual has no recorded predecessor.

Where Each One Wins

The B60 Dual wins in every compute and rendering category where numbers are available. Its FP32 throughput of 12.29 TFLOPS, FP16 throughput of 24.58 TFLOPS, pixel rate of 192.0 GPixel/s, and texture rate of 384.0 GTexel/s all exceed the B390's corresponding figures by wide margins. The B60 Dual's dedicated 24 GB GDDR6 memory with 456.0 GB/s bandwidth also gives it a clear edge in workloads that require large datasets or high memory throughput. The 20 ray tracing cores versus 12 on the B390 further strengthens its position in ray-traced rendering.

The B390's advantages are narrower and tied to its integrated nature. It has a higher boost clock at 2500 MHz versus 2400 MHz, which suggests it can reach slightly higher peak frequencies in short bursts. Its 3 nm process node is a generation ahead of the B60 Dual's 5 nm node, potentially offering better power efficiency per transistor, though the 80 W TDP versus 400 W TDP makes the B390 far more power-frugal. The B390 is an IGP, meaning it requires no separate card slot, no power connectors, and no external display outputs beyond what the portable device provides.

For a mobile or compact system where power draw and physical footprint are primary constraints, the B390's 80 W TDP and IGP form factor are clear advantages. The B60 Dual's 400 W TDP, dual-slot size, and 300 mm length demand a full desktop chassis with substantial cooling and an 800 W suggested power supply.

For dedicated workstation tasks such as large-scale 3D rendering, video processing, or AI inference with FP16 data, the B60 Dual's compute and memory resources make it the stronger choice. The B390's system-shared memory could become a bottleneck in memory-intensive applications, while the B60 Dual operates with a fixed 456.0 GB/s budget.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The Intel Arc Pro B60 Dual delivers 12.29 TFLOPS FP32, which is 60% higher than the Intel Arc Pro B390's 7.680 TFLOPS.

Q: How do the memory configurations differ?

A: The B60 Dual uses 24 GB of GDDR6 on a 192-bit bus with 456.0 GB/s bandwidth. The B390 uses system-shared memory with system-dependent bandwidth, meaning its performance depends entirely on the host platform.

Q: What is the power draw difference?

A: The B390 has an 80 W TDP and requires no power connectors, while the B60 Dual has a 400 W TDP and requires a single 16-pin power connector with a suggested 800 W power supply.

Q: Are there any architectural similarities?

A: Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. However, the B390 uses the Xe3-LPG architecture on a 3 nm Intel process, while the B60 Dual uses Xe2-HPG on a 5 nm TSMC process.

Q: Which GPU has more ray tracing cores?

A: The B60 Dual has 20 ray tracing cores, compared to 12 on the B390.

Q: Can the B390 be installed in a desktop expansion slot?

A: No. The B390 is an integrated graphics processor with an IGP bus interface and no dimensions recorded, while the B60 Dual is a dual-slot PCIe 5.0 x8 card measuring 300 mm by 110 mm by 40 mm.

The Verdict

The data presents a clear performance hierarchy. The Intel Arc Pro B60 Dual outperforms the Intel Arc Pro B390 in every measured compute metric: FP32, FP16, pixel rate, texture rate, shading units, TMUs, ROPs, and ray tracing cores. Its dedicated 24 GB GDDR6 memory with 456.0 GB/s bandwidth removes any dependence on host system memory. For any workload where raw throughput matters, the B60 Dual is the superior choice.

The B390's case rests on its integrated design. At 80 W TDP with no power connectors and IGP slot width, it fits into portable devices where discrete graphics cards are impossible. Its 3 nm process node and 2500 MHz boost clock indicate a modern, efficient design, but the B390's system-shared memory and lower core counts cap its performance ceiling well below the B60 Dual.

Users requiring maximum compute and rendering capability should select the B60 Dual, accepting its 400 W TDP, dual-slot footprint, and 800 W suggested power supply. Users constrained to integrated graphics, such as those in laptops or compact devices, will find the B390 as the only option in this comparison, but they should expect roughly 60% lower FP32 throughput and significantly lower pixel and texture rates based on the recorded specifications.

Specification Differences

| Specification | Intel Arc Pro B390 | Intel Arc Pro B60 Dual |

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

| Architecture | Xe3-LPG | Xe2-HPG |

| Process Node | 3 nm | 5 nm |

| Foundry | Intel | TSMC |

| Chip | Panther Lake | BMG-G21 |

| Transistors | Unknown | 19,600 million |

| Die Size | Unknown | 272 mm² |

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

| Base Clock | 300 MHz | 2000 MHz |

| Boost Clock | 2500 MHz | 2400 MHz |

| Memory Size | System Shared | 24 GB |

| Memory Type | System Shared | GDDR6 |

| Memory Bus Width | System Shared | 192 bit |

| Memory Bandwidth | System Dependent | 456.0 GB/s |

| Memory Clock | System Shared | 2375 MHz, 19 Gbps effective |

| Shading Units | 1536 | 2560 |

| TMUs | 48 | 160 |

| ROPs | 24 | 80 |

| Ray Tracing Cores | 12 | 20 |

| Pixel Rate | 60.00 GPixel/s | 192.0 GPixel/s |

| Texture Rate | 120.0 GTexel/s | 384.0 GTexel/s |

| FP32 | 7.680 TFLOPS | 12.29 TFLOPS |

| FP16 | 15.36 TFLOPS (2:1) | 24.58 TFLOPS (2:1) |

| TDP | 80 W | 400 W |

| Slot Width | IGP | Dual-slot |

| Power Connectors | None | 1x 16-pin |

| Suggested PSU | Not recorded | 800 W |

| Bus Interface | IGP | PCIe 5.0 x8 |

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

| Dimensions | Not recorded | 300 mm x 110 mm x 40 mm |

| Release Date | 2026-01-26 | 2025-09-04 |

| Launch MSRP | Not recorded | 1,199 USD |