Intel Arc A380E x2 vs Intel Arc Pro B65 Comparison

Head-to-Head Benchmarks

The database contains no recorded benchmark scores for either the Intel Arc A380E x2 or the Intel Arc Pro B65. Both products have an average benchmark score of zero and hold the 50th percentile among all GPUs in the database. Consequently, no head-to-head performance comparisons can be derived from measured data. The absence of scores means that any claims about relative speed, frame rates, or compute throughput would be speculative. The Arc Pro B65 specification sheet indicates a significantly higher peak FP32 throughput at 12.29 TFLOPS versus 4.096 TFLOPS for the Arc A380E x2, but without benchmark results, these raw figures remain theoretical maximums rather than observed performance.

Both GPUs share the same API feature set, including DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The recorded data shows identical percentile placement, which reflects the lack of tested workloads rather than equivalence in capability. The Arc Pro B65 has three times the shading units (2560 vs 1024), 2.5 times the texture mapping units (160 vs 64), and 2.5 times the render output units (80 vs 32). These architectural differences would typically translate into substantial performance advantages in rasterization and compute tasks, but the database does not yet include confirmation through benchmark runs.

The pixel rate of the Arc Pro B65 is 192.0 GPixel/s, exactly three times the 64.00 GPixel/s of the Arc A380E x2. Texture rate follows a similar pattern, with 384.0 GTexel/s versus 128.0 GTexel/s. These figures represent theoretical fill rates derived from clock speeds and unit counts. The memory subsystem of the Arc Pro B65 provides 608.0 GB/s of bandwidth, more than three times the 186.0 GB/s available on the Arc A380E x2. Again, these are specification-derived numbers, not measured results, so real-world scaling may differ depending on workload efficiency and driver behavior.

FAQ

Q: Which GPU has more memory bandwidth?

A: The Intel Arc Pro B65 delivers 608.0 GB/s from a 256-bit GDDR6 interface operating at 2375 MHz (19 Gbps effective). The Intel Arc A380E x2 provides 186.0 GB/s from a 96-bit GDDR6 bus at 1937 MHz (15.5 Gbps effective).

Q: What are the transistor counts and die sizes?

A: The Arc Pro B65 uses the BMG-G21 chip with 19,600 million transistors on a 272 mm² die, achieving a transistor density of 72.1M per mm². The Arc A380E x2 uses the DG2-128 chip with 7,200 million transistors on a 157 mm² die, yielding 45.9M transistors per mm².

Q: How do the clock speeds compare?

A: The Arc Pro B65 has base and boost clocks of 2400 MHz, while the Arc A380E x2 has base and boost clocks of 2000 MHz. Both cards run at a fixed clock, with no separate game clock listed for either product.

Q: What power connector does each card require?

A: The Arc A380E x2 uses a single 6-pin power connector and has a 130 W TDP with a suggested PSU of 300 W. The Arc Pro B65 uses a single 8-pin connector, has a 200 W TDP, and requires a suggested PSU of 550 W.

Q: What display outputs are available?

A: The Arc A380E x2 offers 8x mini-DisplayPort 2.0 outputs. The Arc Pro B65 provides 4x DisplayPort 2.1 outputs. The Arc Pro B65 has a dual-slot form factor, while the Arc A380E x2 is single-slot.

Q: When were these products released?

A: The Arc A380E x2 has a release date of 2024-03-31 and its production status is end-of-life. The Arc Pro B65 has a release date of 2026-03-31 and remains active in production.

Architecture Differences

The two GPUs belong to different Intel architectures and generations. The Arc A380E x2 is based on the DG2-128 chip using the Xe-HPG architecture, part of the Alchemist (Arc 3) generation. The Arc Pro B65 uses the BMG-G21 chip with the Xe2-HPG architecture, belonging to the Battlemage (Pro Series) generation. This generational leap brings substantial changes in compute organization, memory subsystem, and feature implementation.

The process technology differs as well. The Arc A380E x2 is fabricated on a 6 nm TSMC process, while the Arc Pro B65 uses a 5 nm TSMC process. The newer node enables higher transistor density, with the Arc Pro B65 packing 72.1M transistors per mm² compared to 45.9M on the older part. Total transistor count rises from 7,200 million to 19,600 million, and die size grows from 157 mm² to 272 mm². The newer chip also runs at higher clocks, with both base and boost speeds at 2400 MHz versus 2000 MHz on the Alchemist card.

The compute architecture scales significantly. Shading units increase from 1024 to 2560, TMUs from 64 to 160, and ROPs from 32 to 80. Ray tracing cores rise from 8 to 20. These changes indicate a broader execution engine capable of handling more parallel workloads. The FP32 throughput jumps from 4.096 TFLOPS to 12.29 TFLOPS, and FP16 (2:1) scales from 8.192 TFLOPS to 24.58 TFLOPS. Neither card lists tensor cores, so AI acceleration relies on the general-purpose shader array.

The memory architecture also differs fundamentally. The Arc A380E x2 uses 6 GB of GDDR6 on a 96-bit bus. The Arc Pro B65 uses 32 GB of GDDR6 on a 256-bit bus. Memory clock rises from 1937 MHz (15.5 Gbps effective) to 2375 MHz (19 Gbps effective). Bandwidth increases from 186.0 GB/s to 608.0 GB/s. This combination of wider bus, faster memory, and larger capacity positions the Arc Pro B65 for memory-intensive workloads such as large model inference, high-resolution rendering, and multi-display configurations.

The bus interface also advances. The Arc A380E x2 connects via PCIe 4.0 x8, while the Arc Pro B65 uses PCIe 5.0 x16. This doubles the available lanes and doubles the per-lane data rate, providing substantially more host bandwidth for data transfer. The Arc Pro B65 also supports DisplayPort 2.1 outputs, whereas the Arc A380E x2 offers mini-DisplayPort 2.0. Both support the same API levels: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Specification Differences

The Arc A380E x2 and Arc Pro B65 differ across nearly every specification field in the database. Process node: 6 nm versus 5 nm. Transistors: 7,200 million versus 19,600 million. Die size: 157 mm² versus 272 mm². Transistor density: 45.9M/mm² versus 72.1M/mm². Base and boost clocks: 2000 MHz versus 2400 MHz. Memory clock: 1937 MHz (15.5 Gbps effective) versus 2375 MHz (19 Gbps effective). Memory size: 6 GB versus 32 GB. Memory type: GDDR6 for both. Bus width: 96 bit versus 256 bit. Bandwidth: 186.0 GB/s versus 608.0 GB/s.

Shader resources differ substantially. Shading units: 1024 versus 2560. TMUs: 64 versus 160. ROPs: 32 versus 80. Ray tracing cores: 8 versus 20. Pixel rate: 64.00 GPixel/s versus 192.0 GPixel/s. Texture rate: 128.0 GTexel/s versus 384.0 GTexel/s. FP32: 4.096 TFLOPS versus 12.29 TFLOPS. FP16 (2:1): 8.192 TFLOPS versus 24.58 TFLOPS. TDP: 130 W versus 200 W.

Physical attributes also diverge. The Arc A380E x2 is single-slot with dimensions of 265 mm length, 127 mm height, and 20 mm width. The Arc Pro B65 is dual-slot, though its dimensions are not recorded in the database. Power connectors: 1x 6-pin versus 1x 8-pin. Suggested PSU: 300 W versus 550 W. Bus interface: PCIe 4.0 x8 versus PCIe 5.0 x16. Display outputs: 8x mini-DisplayPort 2.0 versus 4x DisplayPort 2.1.

Production status and release dates differ as well. The Arc A380E x2 is end-of-life with a release date of 2024-03-31 and a predecessor of Xe Graphics, with a successor listed as Battlemage. The Arc Pro B65 is active, released 2026-03-31, with no predecessor or successor listed. Neither product has a recorded launch MSRP in the database.

The Verdict

The recorded data shows a clear specification hierarchy favoring the Intel Arc Pro B65 across every measurable hardware category. It has more shading units, higher clocks, more memory, wider bus, higher bandwidth, faster fill rates, and greater compute throughput. Its FP32 output of 12.29 TFLOPS is three times the 4.096 TFLOPS of the Arc A380E x2. Memory bandwidth of 608.0 GB/s is more than triple the 186.0 GB/s of the older card. The Arc Pro B65 also uses a newer architecture, newer process node, and newer PCIe interface.

However, the database contains no benchmark results for either GPU, so performance conclusions must remain provisional. The Arc A380E x2 is a single-slot, 130 W card with 8x mini-DisplayPort outputs, suited for dense multi-display installations where board space and power draw are constrained. The Arc Pro B65 is a dual-slot, 200 W card with 4x DisplayPort 2.1 outputs, 32 GB of memory, and a 550 W suggested PSU. Its larger power envelope and physical footprint reflect a design aimed at heavier compute and rendering workloads.

For users prioritizing raw throughput, memory capacity, and bandwidth, the Arc Pro B65 is the clear choice based on specifications alone. For users requiring compact deployment with many display outputs and minimal power draw, the Arc A380E x2 offers a lower-profile option, though its end-of-life status and smaller memory pool limit long-term applicability. The data does not support claims of measured superiority; it only supports differences in hardware capabilities. Actual performance comparisons await benchmark results in the database.