Intel Arc A380E x2 vs Intel Arc B370 Comparison

Intel Arc A380E x2 and Intel Arc B370 occupy very different corners of the hardware landscape. The A380E x2 is a dual-GPU industrial card built on the Alchemist architecture, while the B370 is an integrated graphics processor within the Panther Lake mobile platform. The recorded data shows a clear split in what each component is designed to accomplish, and the benchmark results, though sparse, provide a distinct picture of their relative standing.

Where Each One Wins

The Intel Arc A380E x2 wins in every category related to dedicated graphics throughput and memory bandwidth. Its 6 GB of GDDR6 memory on a 96-bit bus delivers 186.0 GB/s of bandwidth, a figure that is entirely absent for the B370, which relies on System Shared memory with System Dependent bandwidth. The A380E x2 also has a substantial lead in raw pixel and texture processing. It outputs 64.00 GPixel/s compared to the B370’s 48.00 GPixel/s, and its texture rate of 128.0 GTexel/s doubles the B370’s 96.00 GTexel/s.

The Intel Arc B370 wins in the categories of power efficiency and portability. Its 25 W TDP is dramatically lower than the A380E x2’s 130 W, and it requires no power connectors, operating as an integrated graphics processor (IGP). The B370 also has a higher boost clock at 2400 MHz versus the A380E x2’s flat 2000 MHz. Furthermore, the B370 delivers a higher FP32 compute rating of 6.144 TFLOPS, which is 50% higher than the A380E x2’s 4.096 TFLOPS. This suggests the B370 is designed for burst performance in lightweight, mobile scenarios, while the A380E x2 is built for sustained, high-bandwidth output in embedded or multi-display environments.

Architecture Differences

The two GPUs are generations apart. The Intel Arc A380E x2 uses the DG2-128 chip based on the Xe-HPG architecture, part of the Alchemist (Arc 3) generation. It is fabricated on a 6 nm process at TSMC, with 7,200 million transistors on a 157 mm² die, resulting in a transistor density of 45.9M / mm². The Intel Arc B370 uses the Panther Lake chip based on the Xe3-LPG architecture, part of the Arc Graphics-M (Panther Lake) generation, and is built on a 3 nm process at Intel. Its transistor count and die size are unknown in the database.

The core configurations differ significantly. The A380E x2 packs 1024 shading units, 64 TMUs, 32 ROPs, and 8 ray tracing cores. The B370 has 1280 shading units, 40 TMUs, 20 ROPs, and 10 ray tracing cores. This means the B370 has more compute units for shader work and ray tracing, but fewer texture mapping units and ROPs. The A380E x2 compensates with a much higher base clock of 2000 MHz, while the B370 idles at 300 MHz and boosts to 2400 MHz. The memory subsystem is the largest architectural chasm: the A380E x2 has dedicated 6 GB GDDR6 at 1937 MHz, while the B370 has no dedicated memory at all.

The production statuses also differ. The A380E x2 is marked End-of-life, released on 2024-03-31, with a predecessor of Xe Graphics and a successor of Battlemage. The B370 is marked Active, released on 2026-01-26, with no predecessor or successor listed. This indicates the B370 is a current, forward-looking part, while the A380E x2 is from a previous generation cycle.

Head-to-Head Benchmarks

The database contains a single benchmark entry for the Intel Arc B370, the 3dmark_steel_nomad_dx12 test, in which it scored 1184. The Intel Arc A380E x2 has no benchmark scores recorded, meaning the head-to-head comparison is limited to the B370’s absolute performance and its standing among rivals.

The B370’s score of 1184 places it in the 5th percentile of all GPUs, indicating very low overall performance relative to the broader market. Its nearest rivals in the database are all older, low-power parts. The ATI Mobility Radeon HD 5570 scored 1186, which is 0.2% higher than the B370. The ATI Radeon HD 5770 scored 1190, 0.5% higher. The AMD Radeon HD 7650M scored 1192, 0.7% higher. The AMD FirePro M2000 scored 1168, which is 1.4% lower than the B370. This means the B370 is essentially on par with a decade-old mid-range mobile GPU, trailing the closest rival by less than one percent and beating only one of the four listed rivals by a slim margin.

Because the A380E x2 has no recorded benchmark, the data cannot produce a direct score comparison. However, the A380E x2’s 50th percentile standing, coupled with its much higher memory bandwidth and pixel throughput, strongly implies it would outperform the B370 in any GPU-bound workload. The B370’s 5th percentile rank versus the A380E x2’s 50th percentile rank is a stark indicator of their relative market positioning.

FAQ

Q: Which GPU has a higher FP32 compute performance?

A: The Intel Arc B370 has a higher FP32 rating at 6.144 TFLOPS, while the Intel Arc A380E x2 delivers 4.096 TFLOPS. The B370 also leads in FP16 at 12.29 TFLOPS versus 8.192 TFLOPS.

Q: What is the memory configuration difference between the two?

A: The Intel Arc A380E x2 has 6 GB of dedicated GDDR6 memory on a 96-bit bus with 186.0 GB/s bandwidth. The Intel Arc B370 uses System Shared memory with System Dependent bandwidth and no dedicated VRAM.

Q: How do their power requirements compare?

A: The Intel Arc A380E x2 has a 130 W TDP and requires a single 6-pin power connector with a suggested 300 W PSU. The Intel Arc B370 has a 25 W TDP, requires no power connectors, and has no suggested PSU listed.

Q: What are the production statuses of these GPUs?

A: The Intel Arc A380E x2 is End-of-life, released on 2024-03-31. The Intel Arc B370 is Active, released on 2026-01-26.

Q: How does the Intel Arc B370 perform in the recorded benchmark?

A: In the 3dmark_steel_nomad_dx12 test, the B370 scored 1184, placing it in the 5th percentile of all GPUs. Its closest rival, the ATI Mobility Radeon HD 5570, scored 1186, 0.2% higher.

Q: Which GPU has more shading units and ray tracing cores?

A: The Intel Arc B370 has 1280 shading units and 10 ray tracing cores. The Intel Arc A380E x2 has 1024 shading units and 8 ray tracing cores.

Specification Differences

The following fields differ between the Intel Arc A380E x2 and the Intel Arc B370:

• Chip: DG2-128 vs Panther Lake
• Architecture: Xe-HPG vs Xe3-LPG
• Generation: Alchemist (Arc 3) vs Arc Graphics-M (Panther Lake)
• Process Node: 6 nm vs 3 nm
• Foundry: TSMC vs Intel
• Transistors: 7,200 million vs unknown
• Die Size: 157 mm² vs unknown
• Transistor Density: 45.9M / mm² vs null
• Base Clock: 2000 MHz vs 300 MHz
• Boost Clock: 2000 MHz vs 2400 MHz
• Memory Clock: 1937 MHz 15.5 Gbps effective vs System Shared
• Memory Size: 6 GB vs System Shared
• Memory Type: GDDR6 vs System Shared
• Bus Width: 96 bit vs System Shared
• Bandwidth: 186.0 GB/s vs System Dependent
• Shading Units: 1024 vs 1280
• TMUs: 64 vs 40
• ROPs: 32 vs 20
• RT Cores: 8 vs 10
• Pixel Rate: 64.00 GPixel/s vs 48.00 GPixel/s
• Texture Rate: 128.0 GTexel/s vs 96.00 GTexel/s
• FP32: 4.096 TFLOPS vs 6.144 TFLOPS
• FP16: 8.192 TFLOPS (2:1) vs 12.29 TFLOPS (2:1)
• TDP: 130 W vs 25 W
• Slot Width: Single-slot vs IGP
• Power Connectors: 1x 6-pin vs None
• Suggested PSU: 300 W vs null
• Bus Interface: PCIe 4.0 x8 vs IGP
• Display Outputs: 8x mini-DisplayPort 2.0 vs Portable Device Dependent
• Dimensions: 265 mm x 127 mm x 20 mm vs null
• Production Status: End-of-life vs Active
• Release Date: 2024-03-31 vs 2026-01-26
• Predecessor: Xe Graphics vs null
• Successor: Battlemage vs null

The Verdict

The data directs a clear choice based on the use case. The Intel Arc A380E x2 is the superior dedicated graphics solution. It offers vastly more memory bandwidth at 186.0 GB/s, higher pixel and texture rates, and a 50th percentile ranking that is ten times higher than the B370’s 5th percentile. Its 8x mini-DisplayPort 2.0 outputs and PCIe 4.0 x8 interface confirm its role as a multi-display, embedded, or edge-processing card. For any workload that depends on sustained memory access or high fill rates, the A380E x2 is the only viable option among the two.

The Intel Arc B370 is a different class of product. Its 25 W TDP and zero power connectors make it suitable for compact, battery-powered devices. While its FP32 compute is higher at 6.144 TFLOPS, its benchmark score of 1184 places it at the very bottom of the performance spectrum, essentially tied with aging discrete mobile GPUs from over a decade ago. The B370 is not a replacement for the A380E x2 in any performance metric except raw shader math and power draw.

The recorded data shows no overlap in their intended purposes. The A380E x2 is a discontinued, high-bandwidth industrial workhorse. The B370 is an active, low-power integrated component for portable systems. A user requiring graphics acceleration for professional or multi-output applications should select the A380E x2. A user prioritizing minimal power consumption and integrated convenience within a Panther Lake platform should use the B370. The 50th versus 5th percentile gap confirms that the A380E x2 is the performance pick, while the B370 is the efficiency pick.