Intel Arc B570 vs Intel Arc Pro B370 Comparison

Intel Arc B570 is a discrete graphics card built on the Xe2-HPG architecture, featuring the BMG-G21 chip and targeting the Battlemage generation. Intel Arc Pro B370 is an integrated graphics processor based on the Xe3-LPG architecture, using the Panther Lake chip. The database shows the two occupy different performance tiers, with the B570 delivering substantially higher raw throughput while the B370 focuses on efficiency and integration. The recorded data indicates the B570 has a significant advantage in compute and rendering benchmarks, whereas the B370 offers a much lower power envelope. Benchmark results position the B570 in the 65th percentile of all GPUs, while the B370 sits at the 50th percentile, though the B370 has no recorded benchmark scores in the database. The following analysis breaks down the recorded specifications and available performance data for both parts.

Where Each One Wins

The Intel Arc B570 wins in every measurable performance category according to the database. Its average benchmark score of 20556 places it far above the B370, which has an average score of 0 due to lacking any recorded benchmarks. The B570 delivers 11.52 TFLOPS of FP32 compute, nearly double the 6.144 TFLOPS of the B370. In terms of shading units, the B570 has 2304 versus 1280 on the B370, giving it a 44% higher shader count. The B570 also has more texture mapping units (144 vs 40) and more render output units (80 vs 20), resulting in a pixel rate of 200.0 GPixel/s compared to 48.00 GPixel/s and a texture rate of 360.0 GTexel/s versus 96.00 GTexel/s.

The B370 wins in power consumption and physical integration. Its TDP is 25 W, a fraction of the B570's 150 W. The B370 is an IGP with no power connectors and a bus interface of IGP, meaning it requires no separate cooling or slot space. The B370 also uses system shared memory, which eliminates the need for dedicated video memory and simplifies system design. The B370's base clock of 300 MHz is far lower than the B570's 2500 MHz, but its boost clock reaches 2400 MHz, close to the B570's fixed 2500 MHz. The B370 uses a 3 nm process node from Intel, while the B570 uses a 5 nm node from TSMC, indicating a more advanced manufacturing process for the integrated part.

The B570 is the clear winner for discrete graphics performance, while the B370 wins for low-power integrated scenarios. The data shows no overlap in their intended use cases: the B570 targets desktop systems with dedicated power delivery, while the B370 targets portable devices where power draw and physical size are critical. The B570 supports 3x DisplayPort 2.1 and 1x HDMI 2.1a outputs, while the B370's display outputs are portable device dependent, reflecting its integration into mobile platforms.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The Intel Arc B570 has an average benchmark score of 20556, while the Intel Arc Pro B370 has an average score of 0. The B570's nearest rival, the NVIDIA GeForce RTX 3070 Mobile, scores 20534, placing the B570 0.1% ahead in average score.

Q: What is the FP32 compute performance difference?

A: The B570 delivers 11.52 TFLOPS of FP32 compute, while the B370 delivers 6.144 TFLOPS. The B570 has 2304 shading units compared to the B370's 1280, and its texture rate is 360.0 GTexel/s versus 96.00 GTexel/s.

Q: How do the power requirements compare?

A: The B570 has a TDP of 150 W and requires a 1x 8-pin power connector with a suggested PSU of 450 W. The B370 has a TDP of 25 W, uses no power connectors, and has no suggested PSU, as it is an integrated processor.

Q: What memory configurations do the two GPUs use?

A: The B570 has 10 GB of GDDR6 memory on a 160-bit bus with 380.0 GB/s bandwidth. The B370 uses system shared memory, with its type, bus width, and bandwidth all marked as system shared or system dependent.

Q: Which GPU has more render output units?

A: The B570 has 80 ROPs, while the B370 has 20 ROPs. This gives the B570 a pixel rate of 200.0 GPixel/s compared to the B370's 48.00 GPixel/s.

Q: What are the release dates for these GPUs?

A: The B570 was released on 2025-01-15, while the B370 was released on 2026-01-26. The B570 has a launch MSRP of 219 USD, while the B370 has no recorded launch MSRP.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark entries between the Intel Arc B570 and the Intel Arc Pro B370, as indicated by the empty head-to-head benchmarks array. However, the B570 has ten recorded benchmark scores, while the B370 has none. The B570's scores include 2649 in 3dmark steel nomad dx12, 83514 in geekbench opencl, 96844 in geekbench vulkan, and 14195 in passmark g3d. The B370 has zero recorded scores across all benchmark categories.

The B570's individual benchmark results show a wide range of performance across different tests. Its passmark directx 9 score of 164 is more than double its passmark directx 12 score of 72, indicating strong legacy API performance. The passmark g2d score of 661 and gpu compute score of 7281 further demonstrate the B570's capabilities. The B370's lack of benchmark data means no direct comparison can be made from the recorded measurements.

The B570's average benchmark score of 20556 places it in the 65th percentile of all GPUs. Its nearest rivals in the database include the NVIDIA GeForce RTX 3070 Mobile with an average score of 20534 and a delta of 0.1%, the Intel Arc A750 with 20582 and a delta of -0.1%, the NVIDIA Quadro M4000M with 20480 and a delta of 0.4%, and the AMD Radeon R9 M390X with 20662 and a delta of -0.5%. These deltas show the B570 performs within a narrow band of these competing GPUs, with the largest gap being 0.5% behind the AMD Radeon R9 M390X.

The B370 has no nearest rivals listed and no benchmark scores, so its performance position relies solely on its specifications. Its 6.144 TFLOPS of FP32 compute is roughly 53% of the B570's 11.52 TFLOPS, and its 96.00 GTexel/s texture rate is about 27% of the B570's 360.0 GTexel/s. The B370's 48.00 GPixel/s pixel rate is 24% of the B570's 200.0 GPixel/s. These ratios indicate the B370 would fall significantly behind the B570 in any compute-intensive workload.

Specification Differences

The two GPUs differ across nearly every specification field in the database. The B570 uses the BMG-G21 chip with 19,600 million transistors on a 272 mm² die, while the B370 uses the Panther Lake chip with unknown transistor count and die size. The B570 is built on a 5 nm process by TSMC, while the B370 uses a 3 nm process by Intel. The B570's transistor density is 72.1M per mm², while the B370 has no recorded density.

Clock speeds differ substantially. The B570 has a base clock of 2500 MHz and a boost clock of 2500 MHz, effectively a fixed clock. The B370 has a base clock of 300 MHz and a boost clock of 2400 MHz. Memory configurations are entirely different: the B570 has 10 GB of GDDR6 on a 160-bit bus with 380.0 GB/s bandwidth, while the B370 uses system shared memory with no dedicated bandwidth figure.

The B570 has 2304 shading units, 144 TMUs, 80 ROPs, and 18 RT cores. The B370 has 1280 shading units, 40 TMUs, 20 ROPs, and 10 RT cores. The B570's pixel rate is 200.0 GPixel/s and texture rate is 360.0 GTexel/s, while the B370's rates are 48.00 GPixel/s and 96.00 GTexel/s. FP32 performance is 11.52 TFLOPS for the B570 and 6.144 TFLOPS for the B370, with FP16 at 23.04 TFLOPS and 12.29 TFLOPS respectively.

Power and physical dimensions also differ. The B570 has a TDP of 150 W, is dual-slot, requires a 1x 8-pin power connector, and suggests a 450 W PSU. It measures 272 mm in length and 115 mm in height. The B370 has a TDP of 25 W, is an IGP with no slot width, no power connectors, no suggested PSU, and no recorded dimensions. The B570 uses a PCIe 4.0 x8 bus interface, while the B370 uses an IGP interface. Display outputs are 1x HDMI 2.1a and 3x DisplayPort 2.1 on the B570, while the B370's outputs are portable device dependent.

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, according to the database. Neither has recorded tensor cores. The B570 was released on 2025-01-15 with a launch MSRP of 219 USD, while the B370 was released on 2026-01-26 with no launch MSRP. The B570's predecessor is Alchemist, and the B370's predecessor is HD Graphics-WM.

Architecture Differences

The B570 uses the Xe2-HPG architecture, which is the second-generation Xe architecture designed for high-performance graphics. The B370 uses the Xe3-LPG architecture, which is a low-power variant of the third-generation Xe design. The B570 belongs to the Battlemage (Arc 5) generation, while the B370 belongs to the Arc Graphics-WM (Panther Lake) generation. These architecture differences explain the performance gap: Xe2-HPG is optimized for discrete graphics with dedicated memory and high clock speeds, while Xe3-LPG is optimized for integrated use with shared memory and low power draw.

The process nodes differ as well. The B570 is fabricated on a 5 nm process at TSMC, using 19,600 million transistors on a 272 mm² die. The B370 uses a 3 nm process at Intel, with unknown transistor count and die size. The 3 nm node is more advanced, allowing the B370 to achieve higher efficiency despite having fewer shading units. The B570's transistor density of 72.1M per mm² is recorded, while the B370's density is not listed.

Cache and memory architecture also differ. The B570 has 10 GB of dedicated GDDR6 memory with a 160-bit bus, while the B370 relies on system shared memory. This means the B570 has deterministic bandwidth of 380.0 GB/s, while the B370's bandwidth is system dependent. The B570's memory clock is 2375 MHz with 19 Gbps effective speed, while the B370 has no dedicated memory clock.

The RT core counts differ, with the B570 having 18 RT cores and the B370 having 10. The B570's FP32 and FP16 performance are 11.52 TFLOPS and 23.04 TFLOPS respectively, while the B370's are 6.144 TFLOPS and 12.29 TFLOPS. Both maintain a 2:1 FP16 to FP32 ratio. The B570 has a boost clock of 2500 MHz, identical to its base clock, while the B370 has a wide clock range from 300 MHz base to 2400 MHz boost, suggesting dynamic power management for integrated use.

The B570's power connector requirement and dual-slot design indicate it is a standalone card, while the B370's IGP classification means it is embedded in a processor. The B570's display outputs support multiple monitors directly, while the B370's outputs depend on the portable device's implementation. These architecture choices reflect their different market positions: the B570 for desktop gaming and content creation, the B370 for mobile devices where power efficiency is paramount.

The Verdict

The data indicates the Intel Arc B570 is the superior performer for any compute-heavy workload. Its 11.52 TFLOPS FP32, 200.0 GPixel/s pixel rate, and 360.0 GTexel/s texture rate dwarf the B370's 6.144 TFLOPS, 48.00 GPixel/s, and 96.00 GTexel/s. The B570's 10 GB of dedicated GDDR6 memory with 380.0 GB/s bandwidth provides predictable performance, while the B370's system shared memory is system dependent. The B570's 65th percentile ranking among all GPUs, with an average benchmark score of 20556, places it competitively against the NVIDIA GeForce RTX 3070 Mobile, Intel Arc A750, NVIDIA Quadro M4000M, and AMD Radeon R9 M390X, all within a 0.5% delta.

The Intel Arc Pro B370, with no benchmark scores in the database, cannot be directly compared on performance. Its specifications show it is a low-power integrated solution with a 25 W TDP, no power connectors, and an IGP bus interface. The B370's 3 nm process node from Intel and boost clock of 2400 MHz suggest it can reach reasonable performance levels for integrated graphics, but its 1280 shading units and 6.144 TFLOPS FP32 are less than the B570's 2304 units and 11.52 TFLOPS. The B370's 50th percentile ranking reflects its position as an average integrated GPU, though this is based on no recorded benchmark scores.

For users requiring discrete graphics performance, the B570 is the clear choice based on the recorded data. Its launch MSRP of 219 USD positions it in the mid-range market. For portable devices where power draw and integration are priorities, the B370's 25 W TDP and IGP design make it suitable, but its performance remains unmeasured in the database. The B570's release date of 2025-01-15 and the B370's release date of 2026-01-26 indicate the B370 is a newer product, yet the B570's superior specifications and benchmark results show it remains the stronger performer. The choice between the two comes down to the use case: the B570 for dedicated graphics tasks, the B370 for integrated efficiency.