Intel Arc B370 vs Intel Arc Pro B65 Comparison

Intel Arc B370 and Intel Arc Pro B65 occupy different positions in Intel’s graphics lineup, and the recorded data shows a clear split in capability. The B370 is a low-power integrated solution built on the Xe3-LPG architecture, while the Pro B65 is a discrete workstation-oriented card using Xe2-HPG. Benchmark results indicate that the Pro B65 has no recorded 3DMark Steel Nomad score in the database, whereas the B370 posts a score of 1184. That single data point places the B370 in the 5th percentile among all GPUs, with its nearest rivals within a narrow margin. The ATI Mobility Radeon HD 5570 averages 1186, which is 0.2% higher; the ATI Radeon HD 5770 averages 1190, which is 0.5% higher; the AMD Radeon HD 7650M averages 1192, which is 0.7% higher; and the AMD FirePro M2000 averages 1168, which is 1.4% lower. The Pro B65, by contrast, has an average benchmark score of 0 and no nearest rivals listed, indicating an absence of comparable measurements in the current database. Its 50th percentile placement reflects the distribution of all listed GPUs, not a measured score.

Head-to-Head Benchmarks

The head-to-head benchmark table between the Intel Arc B370 and the Intel Arc Pro B65 is empty in the recorded data. No direct comparison tests were logged for these two products. The only available benchmark score belongs to the B370: 1184 in 3DMark Steel Nomad DX12. Against its listed nearest rivals, the B370 trails the ATI Mobility Radeon HD 5570 by 0.2%, the ATI Radeon HD 5770 by 0.5%, and the AMD Radeon HD 7650M by 0.7%. It leads the AMD FirePro M2000 by 1.4%. These deltas are small, all within a range of roughly two percentage points, which indicates that the B370 sits in a tightly clustered performance band around the 1180 to 1190 score range.

The Pro B65 has no benchmark entries in the database. Its average benchmark score is recorded as 0, and its nearest rivals list is empty. Consequently, there is no measured evidence to compare its rasterization performance directly against the B370 in the same test. The percentile fields do provide a secondary comparison: the B370 is at the 5th percentile of all GPUs, while the Pro B65 is at the 50th percentile. That difference is not a score delta, but it does suggest that the Pro B65 is positioned higher in the overall distribution of recorded GPUs. The absence of a direct score for the Pro B65 means that any performance comparison between the two must rely on architectural and specification differences rather than benchmark numbers.

Within the B370’s own results, the pattern is consistent: its score of 1184 is nearly identical to all four nearby rivals. The largest gap is the 1.4% lead over the AMD FirePro M2000, and the largest deficit is the 0.7% gap behind the AMD Radeon HD 7650M. The data does not show any dominant win in either direction for the B370 within its immediate competitive set. For the Pro B65, the lack of a score prevents any direct numeric comparison. The database records winsA and winsB as 0 for both items, confirming that no head-to-head benchmark victories were logged.

Architecture Differences

The two GPUs use different architectures, process nodes, and foundries. The Intel Arc B370 is based on the Xe3-LPG architecture and uses the Panther Lake chip, which places it in the Arc Graphics-M (Panther Lake) generation. Its process node is 3 nm, and the foundry is Intel. The Pro B65 uses the Xe2-HPG architecture with the BMG-G21 chip, part of the Battlemage (Pro Series) generation. Its process node is 5 nm, and the foundry is TSMC. Transistor counts and die sizes differ substantially, though the B370’s figures are recorded as unknown. The Pro B65 has 19,600 million transistors on a 272 mm² die, giving a transistor density of 72.1 million transistors per mm².

Shading resources show a large gap. The B370 has 1280 shading units, 40 texture mapping units, 20 raster output units, and 10 ray tracing cores. The Pro B65 doubles those counts: 2560 shading units, 160 TMUs, 80 ROPs, and 20 ray tracing cores. Neither product lists tensor cores. Clock behavior also differs. The B370 runs at a base clock of 300 MHz and a boost clock of 2400 MHz. The Pro B65 runs at a base clock of 2400 MHz and a boost clock of 2400 MHz, so it has no clock headroom beyond its base. Memory architecture is entirely different: the B370 uses system shared memory, with system shared type, bus width, and system dependent bandwidth. The Pro B65 has 32 GB of GDDR6 memory on a 256-bit bus, with 2375 MHz memory clock (19 Gbps effective) and 608.0 GB/s bandwidth.

Compute rates reflect the resource differences. The B370 delivers 48.00 GPixel/s pixel rate, 96.00 GTexel/s texture rate, 6.144 TFLOPS FP32, and 12.29 TFLOPS FP16 (2:1). The Pro B65 delivers 192.0 GPixel/s, 384.0 GTexel/s, 12.29 TFLOPS FP32, and 24.58 TFLOPS FP16 (2:1). The Pro B65 therefore has four times the pixel and texture throughput and double the FP32 and FP16 throughput. Power and physical requirements are also distinct. The B370 has a TDP of 25 W, an IGP slot width, no power connectors, and an IGP bus interface. The Pro B65 has a TDP of 200 W, a dual-slot design, a single 8-pin power connector, a suggested PSU of 550 W, and a PCIe 5.0 x16 interface. Display outputs differ as well: the B370’s outputs are listed as portable device dependent, while the Pro B65 has 4x DisplayPort 2.1.

API support is identical in the recorded data. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Release dates differ, with the B370 listed as 2026-01-26 and the Pro B65 as 2026-03-31. Both are marked as active production status. Neither has a predecessor or successor listed, and neither has a launch MSRP recorded.

Where Each One Wins

The B370 wins in power efficiency and integration. Its 25 W TDP is far lower than the Pro B65’s 200 W, and its IGP form factor means it requires no power connectors and no separate slot. The B370’s 300 MHz base clock and 2400 MHz boost clock indicate a design that can idle low and ramp up when needed, though the recorded data does not include power measurements beyond TDP. For systems where space and thermal limits are tight, the B370’s integrated nature is a clear advantage. Its system shared memory removes the need for dedicated VRAM allocation, which can simplify system design, though bandwidth becomes system dependent.

The Pro B65 wins in raw compute and memory capacity. Its 32 GB GDDR6 memory with 608.0 GB/s bandwidth provides a dedicated, high-throughput memory subsystem. Its 2560 shading units, 160 TMUs, 80 ROPs, and 20 ray tracing cores give it substantially more parallel processing resources. The Pro B65’s FP32 rate of 12.29 TFLOPS is exactly double the B370’s 6.144 TFLOPS, and its FP16 rate of 24.58 TFLOPS is double the B370’s 12.29 TFLOPS. Pixel rate and texture rate show even larger margins: 192.0 GPixel/s versus 48.00 GPixel/s, and 384.0 GTexel/s versus 96.00 GTexel/s, both fourfold advantages.

The Pro B65 also provides more output flexibility with 4x DisplayPort 2.1, while the B370’s outputs depend on the portable device it is integrated into. The Pro B65’s PCIe 5.0 x16 interface offers a wider system connection than the B370’s IGP bus. In workstation scenarios that require sustained compute, large memory buffers, or multiple high-resolution displays, the Pro B65’s specifications align with those demands. In low-power, portable, or embedded scenarios, the B370’s 25 W envelope and integrated design align with space and thermal constraints.

The recorded benchmark data does not provide direct evidence for either product’s gaming or professional application performance beyond the B370’s single 3DMark Steel Nomad score. The B370’s 1184 score and 5th percentile placement indicate modest absolute performance in that DX12 test. The Pro B65 has no such measurement, so its position in the 50th percentile is not supported by a recorded score. The wins in this section are therefore derived from specification differences: the B370 wins on power and integration, the Pro B65 wins on compute throughput, memory, and display connectivity.

The Verdict

The data supports a clear division. The Intel Arc B370 is suited to systems that require a low-power integrated GPU with no additional power connectors and no dedicated memory. Its 25 W TDP, IGP slot width, and system shared memory make it a fit for compact or portable devices. Its benchmark score of 1184 in 3DMark Steel Nomad DX12 places it at the 5th percentile of all GPUs, and its nearest rivals are all within 1.4% of its score, which indicates that its performance level is comparable to older discrete mobile and desktop parts in that specific test. The B370 uses the Xe3-LPG architecture on Intel’s 3 nm process, which is a newer node than the Pro B65’s 5 nm TSMC process, though the B370’s transistor count and die size are not recorded.

The Intel Arc Pro B65 is suited to systems that need dedicated memory, high compute throughput, and multiple display outputs. Its 32 GB GDDR6 memory, 608.0 GB/s bandwidth, 2560 shading units, and 200 W TDP define it as a discrete, performance-oriented card. Its FP32 rate of 12.29 TFLOPS and FP16 rate of 24.58 TFLOPS are double the B370’s, and its pixel and texture rates are four times higher. The Pro B65’s 4x DisplayPort 2.1 outputs and PCIe 5.0 x16 interface support professional multi-display and high-bandwidth use cases. Its 50th percentile placement in the database indicates a mid-range position among all GPUs, though no direct benchmark score is recorded to confirm absolute performance.

There is no head-to-head benchmark data between the two, so the verdict rests on specifications and the single B370 score. For users who prioritize low power, integration, and minimal system footprint, the B370 is the option supported by the data. For users who prioritize memory capacity, compute throughput, and display flexibility, the Pro B65 is the option supported by the data. Neither product has a launch MSRP recorded, so no price-based comparison is possible. Both are active products with identical API support. The choice between them is a choice between an integrated low-power GPU and a discrete high-throughput GPU, and the specifications reflect that division clearly.

FAQ

Q: What is the benchmark score for the Intel Arc B370?

A: The Intel Arc B370 scores 1184 in 3DMark Steel Nomad DX12. This places it at the 5th percentile among all GPUs in the database.

Q: Does the Intel Arc Pro B65 have a recorded benchmark score?

A: No. The Pro B65 has an empty benchmark list and an average benchmark score of 0 in the database. Its percentile is listed as 50, but no measured score supports that placement.

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

A: The B370’s closest rival is the AMD FirePro M2000, which averages 1168 and is 1.4% lower. The ATI Mobility Radeon HD 5570 averages 1186 and is 0.2% higher, the ATI Radeon HD 5770 averages 1190 and is 0.5% higher, and the AMD Radeon HD 7650M averages 1192 and is 0.7% higher.

Q: What are the memory specifications of the Intel Arc Pro B65?

A: The Pro B65 has 32 GB of GDDR6 memory on a 256-bit bus. The memory clock is 2375 MHz with 19 Gbps effective speed, and bandwidth is 608.0 GB/s. The B370 uses system shared memory with system dependent bandwidth.

Q: What are the power requirements for each GPU?

A: The Intel Arc B370 has a TDP of 25 W, uses an IGP slot width, and has no power connectors. The Intel Arc Pro B65 has a TDP of 200 W, uses a dual-slot design, requires one 8-pin power connector, and has a suggested PSU of 550 W.

Q: Which GPU has more shading units?

A: The Intel Arc Pro B65 has 2560 shading units, while the Intel Arc B370 has 1280 shading units. The Pro B65 also has 160 texture mapping units and 80 raster output units, compared to 40 TMUs and 20 ROPs on the B370.

Specification Differences

| Specification | Intel Arc B370 | Intel Arc Pro B65 |

|---|---|---|

| Architecture | Xe3-LPG | Xe2-HPG |

| Chip | Panther Lake | BMG-G21 |

| Generation | Arc Graphics-M (Panther Lake) | Battlemage (Pro Series) |

| Process node | 3 nm | 5 nm |

| Foundry | Intel | TSMC |

| Transistors | Unknown | 19,600 million |

| Die size | Unknown | 272 mm² |

| Transistor density | Not listed | 72.1M / mm² |

| Base clock | 300 MHz | 2400 MHz |

| Boost clock | 2400 MHz | 2400 MHz |

| Memory clock | System Shared | 2375 MHz (19 Gbps effective) |

| Memory size | System Shared | 32 GB |

| Memory type | System Shared | GDDR6 |

| Memory bus width | System Shared | 256 bit |

| Memory bandwidth | System Dependent | 608.0 GB/s |

| Shading units | 1280 | 2560 |

| TMUs | 40 | 160 |

| ROPs | 20 | 80 |

| Ray tracing cores | 10 | 20 |

| Pixel rate | 48.00 GPixel/s | 192.0 GPixel/s |

| Texture rate | 96.00 GTexel/s | 384.0 GTexel/s |

| FP32 performance | 6.144 TFLOPS | 12.29 TFLOPS |

| FP16 performance | 12.29 TFLOPS (2:1) | 24.58 TFLOPS (2:1) |

| TDP | 25 W | 200 W |

| Slot width | IGP | Dual-slot |

| Power connectors | None | 1x 8-pin |

| Suggested PSU | Not listed | 550 W |

| Bus interface | IGP | PCIe 5.0 x16 |

| Display outputs | Portable Device Dependent | 4x DisplayPort 2.1 |

| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |

| OpenGL | 4.6 | 4.6 |

| Vulkan | 1.4 | 1.4 |

| Release date | 2026-01-26 | 2026-03-31 |

| Production status | Active | Active |

The table above covers only the fields where the two products differ. Shared fields, such as API versions, manufacturer, and active production status, are listed for reference. The B370’s single benchmark score of 1184 and 5th percentile placement contrast with the Pro B65’s empty benchmark record and 50th percentile placement, though the percentile for the Pro B65 is not tied to a recorded measurement. The two GPUs also share identical API support, with both listing DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both have no predecessor, no successor, and no launch MSRP recorded in the database. The B370’s release date precedes the Pro B65’s by roughly two months, with the B370 at 2026-01-26 and the Pro B65 at 2026-03-31.