Intel Arc Pro B70 vs Lisuan Tech LX PRO Comparison

Head-to-Head Benchmarks

The recorded data for the Intel Arc Pro B70 and the Lisuan Tech LX PRO contains no completed benchmark runs. Both entries show an average benchmark score of zero, and the head-to-head benchmark array is empty. Consequently, there are no exact frame rates, render times, or synthetic scores to compare directly. The database indicates a percentile ranking of 50 for both GPUs relative to all other recorded graphics cards, but this value is not tied to any measured performance data. The wins counter shows zero for each product, meaning neither has registered a victory in any comparative test.

This absence of measured results creates an unusual analytical situation. Without benchmark outputs, the only quantitative basis for comparison lies in the specification sheets. The FP32 compute figures offer one of the few direct performance indicators available. The Lisuan Tech LX PRO delivers 24.58 TFLOPS of single-precision compute, while the Intel Arc Pro B70 produces 22.94 TFLOPS. That places the LX PRO approximately 7% ahead of the Arc Pro B70 in raw FP32 throughput. Similarly, FP16 performance favors the LX PRO, with 49.15 TFLOPS versus 45.88 TFLOPS for the Intel part, again a margin of roughly 7% in favor of the Lisuan product.

The pixel and texture rates tell a different story. The Intel Arc Pro B70 achieves a pixel rate of 358.4 GPixel/s, which is 86.7% higher than the 192.0 GPixel/s recorded for the LX PRO. In texture fill, the Arc Pro B70 posts 716.8 GTexel/s against 384.0 GTexel/s for the Lisuan Tech product, a difference of 86.7% as well. These fillrate advantages are substantial and derive from the Intel card's wider memory bus and higher operating clocks, though the absence of measured benchmarks means these rates have not been validated in real workloads.

Memory bandwidth also separates the two. The Arc Pro B70 accesses 608.0 GB/s through a 256-bit bus, while the LX PRO manages 432.0 GB/s across a 192-bit interface. That gives the Intel product a 40.7% bandwidth advantage. The effective memory speed differs as well, with the Arc Pro B70 running at 2375 MHz (19 Gbps effective) and the LX PRO at 2250 MHz (18 Gbps effective). The Intel card also carries 32 GB of GDDR6 memory versus 24 GB on the Lisuan part, a 33.3% capacity advantage.

Where Each One Wins

In the absence of benchmark results, the specification sheet suggests distinct use-case strengths. The Lisuan Tech LX PRO, with its higher FP32 and FP16 throughput, appears positioned for compute-oriented tasks that rely on raw shader math. The 6144 shading units on the LX PRO outnumber the 4096 on the Arc Pro B70 by 50%. Combined with the higher TFLOPS figures, this indicates a design favoring parallel compute workloads such as rendering simulations or scientific calculations, assuming software can utilize the architecture effectively.

The Intel Arc Pro B70 counters with advantages in memory capacity, bandwidth, and fill rates. The 32 GB framebuffer doubles as a practical asset for large dataset handling, and the 608.0 GB/s bandwidth supports high-resolution textures and heavy data streaming. The pixel rate of 358.4 GPixel/s and texture rate of 716.8 GTexel/s suggest strong performance in rasterization-heavy scenarios, assuming the driver stack converts those theoretical rates into actual frames. The Arc Pro B70 also supports PCIe 5.0 x16, while the LX PRO uses PCIe 4.0 x16, which could matter for data transfer speeds in certain workloads.

The LX PRO counters with a 6 nm process node and 24 GB of GDDR6 memory, plus a slightly lower TDP of 225 W against 230 W for the Intel part. The 16-pin power connector on the LX PRO differs from the 8-pin on the Arc Pro B70, though both list 550 W as the suggested PSU. Without real-world tests, these specification-level wins remain hypothetical. The database shows no wins for either product, so any allocation of strengths must rely strictly on the recorded hardware parameters.

Architecture Differences

The Intel Arc Pro B70 uses the BMG-G31 chip built on the Xe2-HPG architecture, belonging to the Battlemage generation labeled as Pro Series. It is manufactured on a 5 nm process at TSMC with a die size of 368 mm². Transistor counts are listed as unknown for both products, preventing a density comparison. The LX PRO uses the 7G105 chip on the TrueGPU architecture, from the 7G100 generation, fabricated on a 6 nm process at TSMC. Its die size is not recorded.

Shader configurations differ significantly. The Arc Pro B70 contains 4096 shading units, 256 texture mapping units, and 128 ROPs. It also includes 32 ray tracing cores. The LX PRO has 6144 shading units, 192 TMUs, and 96 ROPs. No ray tracing core count is listed for the LX PRO, which may indicate a lack of dedicated RT hardware or simply an unrecorded specification. Neither product lists tensor cores, so AI acceleration capabilities remain unquantified in the database.

Memory subsystems diverge in both capacity and interface. The Arc Pro B70 uses 32 GB of GDDR6 with a 256-bit bus and 608.0 GB/s bandwidth. The LX PRO uses 24 GB of GDDR6 with a 192-bit bus and 432.0 GB/s bandwidth. Clock behavior also differs. The Intel part has a base clock of 2280 MHz and a boost clock of 2800 MHz. The LX PRO lists no base or boost clock, only a memory clock of 2250 MHz. This missing data makes clock-for-clock comparisons impossible.

API support shows partial overlap. Both cards support DirectX 12 Ultimate (12_2) and OpenGL 4.6. The Arc Pro B70 supports Vulkan 1.4, while the LX PRO supports Vulkan 1.3, a minor version difference. Display outputs also differ. The Arc Pro B70 provides one HDMI 2.1a port and three DisplayPort 2.1 outputs. The LX PRO provides four DisplayPort 1.4a outputs and no HDMI. The Intel card's DisplayPort 2.1 support is newer than the LX PRO's 1.4a standard.

Physical dimensions vary. The Arc Pro B70 measures 267 mm in length, 110 mm in height, and 39 mm in width. The LX PRO is shorter at 248 mm but taller and thicker, at 118 mm height and 48 mm width. Both are dual-slot cards. The Intel product requires a 1x 8-pin power connector; the LX PRO requires a 1x 16-pin connector. The release dates sit close together, with the Arc Pro B70 appearing on 2026-03-25 and the LX PRO on 2026-03-16, nine days apart.

The Verdict

The data indicates two GPUs with complementary strengths, but the lack of benchmark results prevents a definitive performance ranking. The Lisuan Tech LX PRO holds a clear advantage in raw compute throughput: 24.58 TFLOPS FP32 versus 22.94 TFLOPS, and 49.15 TFLOPS FP16 versus 45.88 TFLOPS. Its 6144 shading units provide 50% more shader cores than the Intel part's 4096. For workloads that scale with shader count and math throughput, the LX PRO appears better suited on paper.

The Intel Arc Pro B70 counters with superior memory resources and fill rates. The 32 GB framebuffer, 608.0 GB/s bandwidth, and 358.4 GPixel/s pixel rate all exceed the LX PRO's corresponding figures by wide margins. The 256-bit bus versus 192-bit, plus the higher effective memory speed, gives the Intel card a substantial data throughput advantage. The presence of 32 ray tracing cores adds a capability that the LX PRO does not list, though the absence of recorded RT core data for the LX PRO leaves this comparison incomplete.

The production status field shows the LX PRO as Active, while the Intel card's status is null. The LX PRO also has no launch MSRP recorded, whereas the Intel card lists a launch MSRP of 949 USD. The suggested PSU is identical at 550 W for both, and TDP values are close at 230 W and 225 W. The process node difference, 5 nm for Intel versus 6 nm for Lisuan Tech, hints at potential efficiency differences, but without measured power or thermal data, the practical impact cannot be assessed.

Ultimately, the database records no test scores, so the verdict rests on specification analysis. The LX PRO appears oriented toward compute-heavy tasks where shader throughput dominates. The Arc Pro B70 appears oriented toward memory-intensive and rasterization-heavy tasks where bandwidth, capacity, and fill rates matter. Neither product has proven its capabilities in recorded benchmarks, so these conclusions remain provisional until measurement data appears.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The Lisuan Tech LX PRO delivers 24.58 TFLOPS FP32, while the Intel Arc Pro B70 delivers 22.94 TFLOPS, putting the LX PRO ahead by approximately 7%.

Q: How much memory bandwidth does each card provide?

A: The Intel Arc Pro B70 provides 608.0 GB/s across a 256-bit bus, while the Lisuan Tech LX PRO provides 432.0 GB/s across a 192-bit bus, giving the Intel card a 40.7% bandwidth advantage.

Q: What are the memory capacities of these two GPUs?

A: The Intel Arc Pro B70 has 32 GB of GDDR6 memory, and the Lisuan Tech LX PRO has 24 GB of GDDR6 memory.

Q: Do both cards support the same DirectX version?

A: Yes, both support DirectX 12 Ultimate (12_2) and OpenGL 4.6. The Vulkan support differs: the Intel card supports Vulkan 1.4, while the LX PRO supports Vulkan 1.3.

Q: What are the physical dimensions of each card?

A: The Intel Arc Pro B70 measures 267 mm long, 110 mm high, and 39 mm wide. The Lisuan Tech LX PRO measures 248 mm long, 118 mm high, and 48 mm wide. Both are dual-slot designs.

Q: Which card has more shading units?

A: The Lisuan Tech LX PRO has 6144 shading units, compared to 4096 on the Intel Arc Pro B70, a 50% higher count.

Specification Differences

| Field | Intel Arc Pro B70 | Lisuan Tech LX PRO |

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

| Chip | BMG-G31 | 7G105 |

| Architecture | Xe2-HPG | TrueGPU |

| Generation | Battlemage (Pro Series) | 7G100 |

| Process Node | 5 nm | 6 nm |

| Die Size | 368 mm² | unknown |

| Base Clock | 2280 MHz | null |

| Boost Clock | 2800 MHz | null |

| Memory Clock | 2375 MHz (19 Gbps effective) | 2250 MHz (18 Gbps effective) |

| Memory Size | 32 GB | 24 GB |

| Memory Bus Width | 256 bit | 192 bit |

| Memory Bandwidth | 608.0 GB/s | 432.0 GB/s |

| Shading Units | 4096 | 6144 |

| TMUs | 256 | 192 |

| ROPs | 128 | 96 |

| Ray Tracing Cores | 32 | null |

| Pixel Rate | 358.4 GPixel/s | 192.0 GPixel/s |

| Texture Rate | 716.8 GTexel/s | 384.0 GTexel/s |

| FP32 | 22.94 TFLOPS | 24.58 TFLOPS |

| FP16 | 45.88 TFLOPS | 49.15 TFLOPS |

| TDP | 230 W | 225 W |

| Power Connector | 1x 8-pin | 1x 16-pin |

| Bus Interface | PCIe 5.0 x16 | PCIe 4.0 x16 |

| Display Outputs | 1x HDMI 2.1a, 3x DisplayPort 2.1 | 4x DisplayPort 1.4a |

| Vulkan Version | 1.4 | 1.3 |

| Dimensions (LxHxW) | 267 mm x 110 mm x 39 mm | 248 mm x 118 mm x 48 mm |

| Release Date | 2026-03-25 | 2026-03-16 |

| Production Status | null | Active |

| Launch MSRP | 949 USD | null |