Intel Arc B370 vs Intel Arc Pro A60M Comparison

The Verdict

The data presents two very different Intel Arc products with almost no direct benchmark overlap. The Intel Arc B370 is an integrated graphics solution built on the Panther Lake platform, while the Intel Arc Pro A60M is a discrete mobile workstation GPU from the Alchemist generation. The B370 has a recorded 3DMark Steel Nomad DX12 score of 1184, placing it in the 5th percentile of all GPUs. The A60M has no recorded benchmark score in the database and sits at the 50th percentile, which is a default position rather than a measured result. The B370's nearest rivals include the ATI Mobility Radeon HD 5570 at 1186 (0.2% ahead), the ATI Radeon HD 5770 at 1190 (0.5% ahead), the AMD Radeon HD 7650M at 1192 (0.7% ahead), and the AMD FirePro M2000 at 1168 (1.4% behind). These are all older mobile and desktop parts, indicating the B370's performance class is modest by modern standards.

The A60M, despite lacking a benchmark score, carries specifications that suggest a different performance tier: 2048 shading units, 128 texture mapping units, 64 raster output units, and 16 ray tracing cores. The B370 counters with 1280 shading units, 40 TMUs, 20 ROPs, and 10 ray tracing cores. The A60M also has dedicated 8 GB GDDR6 memory on a 128-bit bus with 256.0 GB/s bandwidth, while the B370 relies on system shared memory with bandwidth described as system dependent. The A60M's higher pixel rate of 83.20 GPixel/s versus 48.00 GPixel/s and texture rate of 166.4 GTexel/s versus 96.00 GTexel/s reinforce the expectation of higher throughput. The B370 does lead in FP32 compute with 6.144 TFLOPS against the A60M's 5.325 TFLOPS, and in FP16 with 12.29 TFLOPS versus 10.65 TFLOPS, but the A60M's dedicated memory and higher fill rates likely matter more in real workloads.

Users who need a discrete GPU with dedicated VRAM for professional or rendering tasks should look toward the A60M. Users constrained to an integrated solution with no additional power connectors and a 25 W TDP should consider the B370. The A60M's 95 W TDP and PCIe 4.0 x16 interface indicate a different platform requirement, while the B370's IGP bus interface and 3 nm process point to an embedded or mobile SoC context. The benchmark data does not support a direct performance comparison, so the verdict rests on architectural and specification differences.

Architecture Differences

The B370 uses the Xe3-LPG architecture on a 3 nm process node fabricated by Intel. It belongs to the Arc Graphics-M (Panther Lake) generation. The A60M uses the Xe-HPG architecture on a 6 nm process node fabricated by TSMC, belonging to the Alchemist (Pro-Series Mobile) generation. The process node difference is significant: 3 nm versus 6 nm suggests the B370 benefits from a more advanced manufacturing technology, potentially improving power efficiency and transistor density. The A60M's die size is recorded as 269 mm² with 11,500 million transistors and a transistor density of 42.8M per mm². The B370's transistor count and die size are listed as unknown, so no direct density comparison is possible.

The B370's rendering pipeline is smaller across the board. It has 1280 shading units, 40 TMUs, and 20 ROPs. The A60M has 2048 shading units, 128 TMUs, and 64 ROPs. The A60M's TMU count is more than three times that of the B370, and its ROP count is more than three times as well. Ray tracing resources also differ: the B370 has 10 ray tracing cores, while the A60M has 16. The B370's clock behavior is unusual, with a base clock of 300 MHz and a boost clock of 2400 MHz. The A60M has a base clock of 900 MHz and a boost clock of 1300 MHz. The B370's wide clock range indicates it can scale aggressively under load, but its lower base suggests power management is a priority.

Memory architecture is another major division. The B370 uses system shared memory with no dedicated VRAM, a system-dependent bandwidth, and a system shared bus width. The A60M uses 8 GB of GDDR6 memory with a 128-bit bus and a fixed 256.0 GB/s bandwidth. The memory clock for the A60M is listed as 2000 MHz with 16 Gbps effective. This dedicated memory configuration gives the A60M predictable memory performance, whereas the B370's memory performance varies with the host system. Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API compatibility is identical. Neither lists tensor cores, and both have portable device dependent display outputs.

Head-to-Head Benchmarks

The head-to-head benchmark array in the database is empty, and the B370 has only one recorded benchmark while the A60M has none. The B370's single result is 1184 in 3dmark_3dmark_steel_nomad_dx12. Its nearest rival, the ATI Mobility Radeon HD 5570, scores 1186, which is 0.2% higher. The ATI Radeon HD 5770 scores 1190, 0.5% higher, and 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 small, all within 1.5 percentage points. The B370's 5th percentile ranking places it far below most GPUs in the database, but its nearest competitors are all older parts, suggesting its absolute score is modest yet competitive with that older class.

The A60M's lack of benchmark data means no direct comparison can be made from recorded scores. Its 50th percentile is a placeholder, not a measured result. The database shows zero wins for each side in the head-to-head section, reflecting the absence of shared tests. The specification gaps fill this void: the A60M's fill rates are substantially higher, with a pixel rate of 83.20 GPixel/s versus 48.00 GPixel/s, and a texture rate of 166.4 GTexel/s versus 96.00 GTexel/s. These are 73% and 73% higher, respectively. The B370's FP32 throughput of 6.144 TFLOPS is 15% higher than the A60M's 5.325 TFLOPS, and its FP16 throughput of 12.29 TFLOPS is 15% higher than 10.65 TFLOPS. The compute advantage does not translate to fill rate advantages, which are dominated by the A60M's larger ROP and TMU counts.

The B370's boost clock of 2400 MHz is 85% higher than the A60M's 1300 MHz, which explains how fewer shading units can produce higher TFLOPS. The A60M compensates with more units at lower clocks. The B370's TDP of 25 W is 74% lower than the A60M's 95 W, indicating a power efficiency advantage for the integrated part. The A60M's 8 GB GDDR6 memory with 256.0 GB/s bandwidth versus system shared memory is a structural advantage for memory-intensive workloads. The recorded data does not show a single test where both parts appear, so conclusions about relative performance must be inferred from these specifications.

Specification Differences

The two GPUs differ in nearly every measurable specification. The process node is 3 nm for the B370 versus 6 nm for the A60M, with the B370 fabricated by Intel and the A60M by TSMC. The A60M has a known transistor count of 11,500 million, a die size of 269 mm², and a density of 42.8M per mm²; the B370 lists all three as unknown. The B370's base clock is 300 MHz with a 2400 MHz boost, while the A60M's base is 900 MHz with a 1300 MHz boost. The A60M's memory clock is 2000 MHz with 16 Gbps effective, while the B370's memory clock is system shared. Memory size, type, bus width, and bandwidth all differ: the B370 is system shared, while the A60M has 8 GB GDDR6, a 128-bit bus, and 256.0 GB/s bandwidth.

Shading units are 1280 for the B370 versus 2048 for the A60M. TMUs are 40 versus 128. ROPs are 20 versus 64. Ray tracing cores are 10 versus 16. Pixel rate is 48.00 GPixel/s versus 83.20 GPixel/s. Texture rate is 96.00 GTexel/s versus 166.4 GTexel/s. FP32 is 6.144 TFLOPS versus 5.325 TFLOPS. FP16 is 12.29 TFLOPS versus 10.65 TFLOPS. TDP is 25 W versus 95 W. The bus interface is IGP for the B370 and PCIe 4.0 x16 for the A60M. The B370 has no power connectors, while the A60M's power connector field is null. Both have portable device dependent display outputs. API support is identical: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The B370's release date is 2026-01-26, while the A60M's is 2023-06-05. Neither has a launch MSRP listed.

FAQ

Q: Which GPU has a higher recorded benchmark score?

A: Only the Intel Arc B370 has a recorded benchmark score in the database. It scores 1184 in 3dmark_3dmark_steel_nomad_dx12. The Intel Arc Pro A60M has no recorded benchmark scores, with an average score of 0.

Q: How does the Intel Arc B370 compare to its nearest rivals?

A: The B370 scores 1184, while the ATI Mobility Radeon HD 5570 scores 1186 (0.2% higher), the ATI Radeon HD 5770 scores 1190 (0.5% higher), the AMD Radeon HD 7650M scores 1192 (0.7% higher), and the AMD FirePro M2000 scores 1168 (1.4% lower). The B370's percentile vs all GPUs is 5.

Q: What memory configuration does each GPU use?

A: The Intel Arc B370 uses system shared memory with system dependent bandwidth and a system shared bus width. The Intel Arc Pro A60M uses 8 GB of GDDR6 memory with a 128-bit bus and 256.0 GB/s bandwidth, with a memory clock of 2000 MHz and 16 Gbps effective.

Q: Which GPU has higher fill rates?

A: The Intel Arc Pro A60M has a pixel rate of 83.20 GPixel/s and a texture rate of 166.4 GTexel/s. The Intel Arc B370 has a pixel rate of 48.00 GPixel/s and a texture rate of 96.00 GTexel/s. The A60M is higher in both.

Q: Which GPU has higher compute throughput?

A: The Intel Arc B370 has higher FP32 compute at 6.144 TFLOPS versus the A60M's 5.325 TFLOPS, and higher FP16 at 12.29 TFLOPS versus 10.65 TFLOPS. The B370 leads by 15% in both metrics.

Q: What are the power consumption differences?

A: The Intel Arc B370 has a TDP of 25 W with no power connectors and an IGP bus interface. The Intel Arc Pro A60M has a TDP of 95 W and uses a PCIe 4.0 x16 bus interface. The B370's TDP is 74% lower.

Where Each One Wins

The Intel Arc B370 wins on compute density per watt. Its FP32 throughput of 6.144 TFLOPS at a 25 W TDP yields a compute-to-power ratio that the A60M cannot match with 5.325 TFLOPS at 95 W. The B370's 3 nm process node and 2400 MHz boost clock explain this efficiency. The B370 is also the only one of the two with a recorded benchmark score, so it has a measurable baseline in the database. Its 1184 Steel Nomad result, while in the 5th percentile, puts it within 1% of several older ATI and AMD parts, meaning it can trade blows with that generation of hardware. The B370's integrated nature, with no power connectors and an IGP bus, makes it suitable for compact systems where a discrete GPU cannot fit.

The Intel Arc Pro A60M wins on raw graphics throughput and memory bandwidth. Its pixel rate of 83.20 GPixel/s is 73% higher than the B370's 48.00 GPixel/s, and its texture rate of 166.4 GTexel/s is 73% higher than 96.00 GTexel/s. The A60M's 2048 shading units, 128 TMUs, and 64 ROPs provide a much larger rendering pipeline. Its dedicated 8 GB GDDR6 memory with 256.0 GB/s bandwidth is a clear advantage for workloads that need consistent memory access, whereas the B370's system shared memory bandwidth is system dependent and variable. The A60M's 16 ray tracing cores versus 10 also suggest better ray tracing throughput. Its PCIe 4.0 x16 interface and 95 W TDP indicate it is designed for a mobile workstation chassis with proper cooling and power delivery.

The use-case split is clear. The B370 serves as a low-power integrated solution for Panther Lake-based systems where no discrete GPU is present. It offers competitive compute for its 25 W envelope and can handle workloads that fit within system shared memory. The A60M serves as a discrete mobile GPU for professional applications that require dedicated VRAM, high fill rates, and a larger shading array. The A60M's 50th percentile ranking, though not a measured score, places it in a higher database position than the B370's 5th percentile. The A60M's release date of 2023-06-05 also predates the B370's 2026-01-26 release, indicating a different product lifecycle stage. For users who need dedicated memory and higher rasterization throughput, the A60M is the data-supported choice. For users who need compute throughput at minimal power draw, the B370 is the only option with recorded performance data.