Intel Arc A570M vs Intel Arc Pro B370 Comparison

Head-to-Head Benchmarks

The recorded data contains a single benchmark result for the Intel Arc A570M, the Geekbench OpenCL score of 58239. This places the A570M in the 88th percentile of all GPUs in the database. The Intel Arc Pro B370 currently has no benchmark scores recorded, so a direct numerical comparison between these two specific parts is not possible from the available measurements.

Without a recorded score for the Arc Pro B370, the analysis must rely on the A570M's position relative to its nearest rivals. The A570M is 0.3% ahead of the AMD Radeon RX 5600 OEM (score 58085) and 0.3% behind the AMD Radeon RX 6950 XT (score 58392). It also trails the NVIDIA P102-100 by 0.5% (score 58528) and the AMD Radeon PRO V710 by 0.7% (score 58657). These deltas indicate the A570M sits in a tightly contested performance band, where the spread between the closest competitors is less than one percent.

The absence of any head-to-head benchmark data means the A570M's single score of 58239 stands as the only quantitative performance anchor in this comparison. The Arc Pro B370, with an average benchmark score of 0 and no rivals listed, cannot be positioned relative to the A570M using the database measurements. The A570M's score of 58239 suggests it operates within the range of high-end desktop discrete GPUs from the previous generation, despite its mobile-oriented 75 W TDP. The Arc Pro B370's 25 W TDP and integrated nature indicate a fundamentally different performance class, but the data does not yet quantify this difference.

The Verdict

The data indicates that the Intel Arc A570M is the only one of these two parts with measurable benchmark performance. Its Geekbench OpenCL score of 58239 and 88th percentile ranking demonstrate that it delivers competitive results against established discrete GPUs. The Arc Pro B370, by contrast, has no recorded benchmarks and a 50th percentile baseline, which in the database reflects an unmeasured state rather than a specific performance level.

For users selecting a part based on available data, the A570M is the clear choice when performance evidence matters. Its score positions it within 0.7% of the AMD Radeon PRO V710 and within 0.5% of the NVIDIA P102-100, indicating that it competes directly with these workstation-oriented cards. The Arc Pro B370 cannot be recommended on the strength of benchmark data because none exists in the database.

However, the Arc Pro B370's integrated design and 25 W TDP suggest a different use case entirely. The A570M is a discrete mobile GPU with 8 GB of dedicated GDDR6 memory and a 128-bit bus, while the B370 relies on system shared memory and has no dedicated VRAM. The B370's predecessor is listed as HD Graphics-WM, which places it in the integrated graphics lineage rather than the discrete Arc 5 Mobile series. The verdict from the data is straightforward: the A570M has proven performance, the B370 does not yet have recorded performance to evaluate.

Architecture Differences

The two GPUs come from different architectural generations and manufacturing processes. The Intel Arc A570M uses the DG2-256 chip built on the Xe-HPG architecture, which belongs to the Alchemist generation (Arc 5 Mobile). This chip is fabricated on a 6 nm process at TSMC and contains 11,500 million transistors on a 269 mm² die, yielding a transistor density of 42.8 million per square millimeter.

The Intel Arc Pro B370 uses the Panther Lake chip with the Xe3-LPG architecture, in the Arc Graphics-WM (Panther Lake) generation. It is fabricated on a 3 nm process at Intel, with transistor count and die size listed as unknown. The architecture shift from Xe-HPG to Xe3-LPG represents a generational jump, but the database does not provide functional details about the differences beyond the chip name and process node.

The process node difference is significant: 6 nm at TSMC versus 3 nm at Intel. The A570M's larger die and transistor count reflect its discrete design, while the B370's unknown transistor data aligns with its integrated nature. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API compatibility is identical across the two.

The A570M includes 16 ray tracing cores and 2048 shading units, while the B370 has 10 ray tracing cores and 1280 shading units. Neither part lists tensor cores. The A570M has a pixel rate of 83.20 GPixel/s and a texture rate of 166.4 GTexel/s, while the B370 delivers 48.00 GPixel/s and 96.00 GTexel/s. These throughput differences are direct consequences of the shading unit and TMU counts, with the A570M having 128 TMUs against the B370's 40.

Specification Differences

The most prominent specification difference is memory. The A570M has 8 GB of GDDR6 on a 128-bit bus with 224.0 GB/s bandwidth, while the B370 uses system shared memory with system dependent bandwidth. The B370's memory type, size, and bus width are all listed as "System Shared," meaning it has no dedicated VRAM.

Clock speeds differ substantially. The A570M has a 900 MHz base clock and a 1300 MHz boost clock, with memory clocked at 1750 MHz (14 Gbps effective). The B370 has a 300 MHz base clock and a 2400 MHz boost clock, with memory clocked as "System Shared." The B370's boost clock is nearly double the A570M's, but the A570M's dedicated memory bandwidth of 224.0 GB/s is a significant advantage for graphics workloads.

Power consumption differs by a factor of three: the A570M has a 75 W TDP, while the B370 has a 25 W TDP. Both are listed as IGP slot width. The A570M uses a PCIe 4.0 x8 bus interface, while the B370 uses IGP for its bus interface, consistent with its integrated design. The B370 lists no power connectors, while the A570M has none listed either.

The release dates differ: the A570M was released on 2023-07-31, and the B370 on 2026-01-26. The B370's predecessor is HD Graphics-WM, while the A570M has no listed predecessor. The B370 also lists a successor of none, and the A570M has no successor listed. The A570M's shading units (2048), TMUs (128), and ROPs (64) all exceed the B370's corresponding counts of 1280, 40, and 20.

The compute throughput figures show a different relationship than the clock speeds. The A570M delivers 5.325 TFLOPS FP32 and 10.65 TFLOPS FP16 (2:1), while the B370 delivers 6.144 TFLOPS FP32 and 12.29 TFLOPS FP16 (2:1). Despite having fewer shading units, the B370 achieves higher FP32 and FP16 throughput because of its much higher boost clock.

FAQ

Q: Which GPU has more shading units?

A: The Intel Arc A570M has 2048 shading units, while the Intel Arc Pro B370 has 1280 shading units.

Q: How much memory bandwidth does the A570M provide?

A: The A570M provides 224.0 GB/s of bandwidth through 8 GB of GDDR6 on a 128-bit bus. The B370 uses system shared memory with system dependent bandwidth.

Q: What are the FP32 performance figures for each GPU?

A: The A570M delivers 5.325 TFLOPS FP32, while the B370 delivers 6.144 TFLOPS FP32, making the B370 higher in raw FP32 throughput despite its lower shading unit count.

Q: Do both GPUs support the same APIs?

A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What is the TDP difference between the two?

A: The A570M has a 75 W TDP, and the B370 has a 25 W TDP.

Q: Which GPU has a higher boost clock?

A: The B370 has a 2400 MHz boost clock, while the A570M has a 1300 MHz boost clock. The A570M has a higher base clock at 900 MHz versus the B370's 300 MHz.