Intel Arc A380M vs Intel Arc B370 Comparison

The Verdict

The data presents two fundamentally different Intel Arc mobile graphics solutions. The Intel Arc A380M is a discrete MXM module built on the Alchemist architecture, while the Intel Arc B370 is an integrated graphics processor (IGP) embedded within the Panther Lake chip. Based on the recorded benchmark results, the Arc B370 delivers a single 3DMark Steel Nomad DX12 score of 1184, placing it in the 5th percentile of all GPUs. The Arc A380M has no recorded benchmark scores in the database, so its performance cannot be directly quantified. However, its architectural specifications suggest a very different performance profile.

The Arc B370's nearest rivals in the database are all older ATI and AMD parts. It sits within 0.7% of the ATI Mobility Radeon HD 5570, ATI Radeon HD 5770, and AMD Radeon HD 7650M, and it is 1.4% ahead of the AMD FirePro M2000. This indicates that the integrated Arc B370, despite its modern architecture, produces performance in line with those legacy discrete cards in this specific DirectX 12 test. The Arc A380M, lacking any benchmark entries, cannot be compared in this manner. The verdict points to the Arc B370 for users who need a low-power integrated solution with a confirmed, albeit modest, benchmark footprint, while the Arc A380M remains a more capable discrete option on paper, with higher pixel fill rate and texture rate, but no measured data to confirm its standing.

Where Each One Wins

The Arc A380M wins on raw computational throughput and memory bandwidth based on its specifications. It delivers 4.096 TFLOPS of FP32 performance, has a 96-bit memory bus with 186.0 GB/s of dedicated GDDR6 bandwidth, and operates with a 35 W TDP. The Arc B370 counters with a higher FP32 figure of 6.144 TFLOPS, a 2400 MHz boost clock, and a substantially lower 25 W TDP. The Arc B370 also has more shading units at 1280 versus 1024 for the A380M, and more ray tracing cores at 10 versus 8.

However, the Arc A380M wins on memory architecture. It uses 6 GB of dedicated GDDR6 memory, while the Arc B370 relies on System Shared memory with bandwidth described as System Dependent. The A380M also has a higher pixel rate at 64.00 GPixel/s versus 48.00 GPixel/s for the B370, and a higher texture rate at 128.0 GTexel/s versus 96.00 GTexel/s. The A380M wins on process maturity for discrete deployment as an MXM Module, while the B370 is an IGP with no power connectors. For users with a portable device that supports MXM upgrades, the A380M is the clear choice. For users with a Panther Lake platform where an IGP is the only option, the B370 is the sole contender.

Architecture Differences

The two GPUs represent different generations and design philosophies from Intel. The Arc A380M uses the DG2-128 chip built on the Xe-HPG architecture, belonging to the Alchemist generation for Arc 3 Mobile. It is fabricated on a 6 nm process at TSMC, with 7,200 million transistors on a 157 mm² die, yielding a transistor density of 45.9M per mm². Its base clock is 1550 MHz with a boost clock of 2000 MHz, and its memory runs at 1937 MHz, translating to 15.5 Gbps effective.

The Arc B370 uses the Panther Lake chip built on the Xe3-LPG architecture, belonging to the Arc Graphics-M generation for Panther Lake. It is fabricated on a 3 nm process at Intel, though its transistor count, die size, and transistor density are listed as unknown. Its base clock is notably lower at 300 MHz, but its boost clock is higher at 2400 MHz. Its memory is System Shared, meaning the GPU uses the host system's memory rather than dedicated VRAM.

The A380M has 64 texture mapping units and 32 ROPs, while the B370 has 40 TMUs and 20 ROPs. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The A380M is an MXM Module with an MXM-A (3.1) bus interface and no power connectors listed, while the B370 is an IGP with no power connectors and an IGP bus interface. Both have display outputs described as Portable Device Dependent. The A380M was released in January 2023, while the B370 is slated for release in January 2026.

FAQ

Q: Which GPU has a higher boost clock?

A: The Intel Arc B370 has a boost clock of 2400 MHz, which is higher than the Intel Arc A380M's boost clock of 2000 MHz.

Q: How much dedicated memory does the Arc A380M have?

A: The Arc A380M has 6 GB of GDDR6 memory on a 96-bit bus, providing 186.0 GB/s of bandwidth.

Q: What is the memory configuration of the Arc B370?

A: The Arc B370 uses System Shared memory, meaning it relies on the host system's memory rather than dedicated VRAM, with bandwidth described as System Dependent.

Q: Which GPU has more shading units?

A: The Arc B370 has 1280 shading units, while the Arc A380M has 1024 shading units.

Q: What is the power envelope of each GPU?

A: The Arc A380M has a TDP of 35 W, while the Arc B370 has a lower TDP of 25 W.

Q: How does the Arc B370 compare to its nearest rival in the database?

A: The Arc B370's score of 1184 in 3DMark Steel Nomad DX12 is 0.2% behind the ATI Mobility Radeon HD 5570, 0.5% behind the ATI Radeon HD 5770, 0.7% behind the AMD Radeon HD 7650M, and 1.4% ahead of the AMD FirePro M2000.

Head-to-Head Benchmarks

The database contains no head-to-head benchmark entries between the Intel Arc A380M and the Intel Arc B370. The only recorded benchmark in the entire dataset belongs to the Arc B370: a 3DMark Steel Nomad DX12 score of 1184. This score places the B370 in the 5th percentile of all GPUs, indicating that it sits in the lower performance tier of the database.

The Arc B370's nearest rivals provide context for this score. The ATI Mobility Radeon HD 5570 has an average score of 1186, which is 0.2% higher than the B370's result. The ATI Radeon HD 5770 scores 1190, 0.5% higher. The AMD Radeon HD 7650M scores 1192, 0.7% higher. The AMD FirePro M2000 scores 1168, which is 1.4% lower than the B370. These deltas are all within a narrow 2.1% band, showing that the Arc B370's integrated performance is closely matched with these older discrete GPUs in this specific DirectX 12 workload.

For the Arc A380M, the database lists no benchmarks and no nearest rivals. Its average benchmark score is recorded as 0, and it has a percentile ranking of 50, which is the median position in the database, but this is not supported by any actual test data. The A380M's specification sheet shows a theoretical FP32 throughput of 4.096 TFLOPS, which is lower than the B370's 6.144 TFLOPS. However, the A380M's dedicated memory bandwidth of 186.0 GB/s is a concrete advantage over the B370's System Shared configuration, where bandwidth is dependent on the host platform. The A380M also shows higher pixel and texture rates, at 64.00 GPixel/s and 128.0 GTexel/s respectively, compared to the B370's 48.00 GPixel/s and 96.00 GTexel/s.

The release timeline also differs. The Arc A380M launched in January 2023, making it the earlier product. The Arc B370 is scheduled for release in January 2026. The A380M uses a 6 nm TSMC process with 7,200 million transistors, while the B370 uses a 3 nm Intel process with unknown transistor counts. The A380M's die size is 157 mm², while the B370's die size is also unknown. The A380M is a discrete MXM module, while the B370 is an IGP. These structural differences mean that the B370's integrated nature likely benefits from the newer process node, but its performance ceiling is constrained by shared system memory and a lower TDP of 25 W compared to the A380M's 35 W.

In the absence of direct benchmark comparisons, the data shows two separate performance stories. The B370 has a measured, if modest, result that aligns with legacy discrete GPUs. The A380M has no measured result, so its actual performance cannot be verified from the database. Analysts must rely on the recorded specifications, which show the A380M as a higher-bandwidth, higher-fill-rate part with dedicated memory, while the B370 offers higher raw FP32 compute but depends entirely on the host system for memory. The recorded data supports the B370 as a verified performer for integrated graphics, while the A380M remains an unverified discrete option with stronger memory and rasterization specifications on paper.