Intel Arc Pro B370 vs NVIDIA N1 20SM Comparison

The Verdict

The data indicates two fundamentally different integrated graphics solutions. The Intel Arc Pro B370, built on a 3 nm process with the Xe3-LPG architecture, is positioned as a DirectX 12 Ultimate capable IGP with modern API support. The NVIDIA N1 20SM, using a 5 nm TSMC process with Blackwell 2.0 architecture, offers significantly higher raw compute throughput and a vastly larger memory subsystem, but lacks any DirectX, OpenGL, or Vulkan API support in the recorded data.

From the specifications, the NVIDIA N1 20SM is the clear choice for compute-heavy workloads that can leverage its 12.01 TFLOPS FP32 performance and 273.2 GB/s memory bandwidth. The Intel Arc Pro B370, with 6.144 TFLOPS FP32 and system-shared memory, is the only option for graphics rendering tasks requiring standard graphics APIs. The Intel part also consumes a rated 25 W, while the NVIDIA part has an unknown TDP, making direct efficiency comparisons impossible with the available data. The Intel Arc Pro B370 suits portable devices needing modern graphics API support, while the NVIDIA N1 20SM suits high-bandwidth compute tasks, provided the software stack does not rely on conventional graphics APIs.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The NVIDIA N1 20SM delivers 12.01 TFLOPS FP32, which is roughly double the 6.144 TFLOPS of the Intel Arc Pro B370.

Q: What are the memory configurations?

A: The NVIDIA N1 20SM has 128 GB of LPDDR5X memory on a 256-bit bus with 273.2 GB/s bandwidth. The Intel Arc Pro B370 uses System Shared memory with System Dependent bandwidth.

Q: Which GPU supports DirectX 12 Ultimate?

A: Only the Intel Arc Pro B370 supports DirectX 12 Ultimate (12_2), along with OpenGL 4.6 and Vulkan 1.4. The NVIDIA N1 20SM has no DirectX, OpenGL, or Vulkan support listed.

Q: How do the shading unit counts compare?

A: The NVIDIA N1 20SM has 2560 shading units, exactly double the 1280 shading units in the Intel Arc Pro B370.

Q: What is the process node difference?

A: The Intel Arc Pro B370 uses a 3 nm process from Intel, while the NVIDIA N1 20SM uses a 5 nm process from TSMC.

Q: What is the boost clock difference?

A: The Intel Arc Pro B370 boosts to 2400 MHz, slightly higher than the NVIDIA N1 20SM which boosts to 2346 MHz.

Architecture Differences

The Intel Arc Pro B370 is built on the Xe3-LPG architecture and belongs to the Arc Graphics-WM (Panther Lake) generation. Its chip is named Panther Lake, fabricated on a 3 nm process at Intel. The architecture supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, making it a fully featured graphics solution for standard rendering pipelines. The NVIDIA N1 20SM uses the Blackwell 2.0 architecture, with the chip GB20B, part of the Blackwell IGP (N1x) generation, manufactured by TSMC on a 5 nm process with a die size of 382 mm². The NVIDIA part has no graphics API support listed, which suggests it is designed for compute or specialized tasks rather than traditional graphics rendering.

The Intel part integrates 10 ray tracing cores, while the NVIDIA part has 20 RT cores and 80 tensor cores. The Intel part does not list tensor cores. Texture mapping units differ substantially: the NVIDIA N1 20SM has 160 TMUs versus 40 on the Intel Arc Pro B370. Render output units are 24 on NVIDIA and 20 on Intel. The NVIDIA part also uses a PCIe 5.0 x16 bus interface, whereas the Intel part uses an IGP bus interface. Display outputs also differ: the Intel part is listed as Portable Device Dependent, while the NVIDIA part has a single HDMI output.

Specification Differences

The two GPUs differ across nearly every measurable specification. The Intel Arc Pro B370 has a base clock of 300 MHz and a boost clock of 2400 MHz, while the NVIDIA N1 20SM has a base clock of 741 MHz and a boost clock of 2346 MHz. Memory is a major divergence: the Intel part uses System Shared memory with System Dependent bandwidth, while the NVIDIA part uses 128 GB of LPDDR5X on a 256-bit bus with 273.2 GB/s bandwidth. The NVIDIA memory clock is listed as 1067 MHz with 8.5 Gbps effective.

Shading units: 1280 on Intel versus 2560 on NVIDIA. TMUs: 40 versus 160. ROPs: 20 versus 24. RT cores: 10 versus 20. Tensor cores: not listed on Intel versus 80 on NVIDIA. Pixel rate is 48.00 GPixel/s on Intel versus 56.30 GPixel/s on NVIDIA. Texture rate is 96.00 GTexel/s on Intel versus 375.4 GTexel/s on NVIDIA, a nearly 4x difference. FP32 compute is 6.144 TFLOPS on Intel versus 12.01 TFLOPS on NVIDIA. FP16 is 12.29 TFLOPS (2:1) on Intel versus 12.01 TFLOPS (1:1) on NVIDIA.

Power: the Intel Arc Pro B370 is rated at 25 W TDP with no power connectors. The NVIDIA N1 20SM has an unknown TDP and no power connectors. Both are IGP slot width. The Intel part has no listed dimensions, the NVIDIA die size is 382 mm². Release dates differ: the Intel part was released on 2026-01-26, the NVIDIA part on 2026-05-31. The Intel part's predecessor is HD Graphics-WM, the NVIDIA part has no predecessor. Neither has a launch MSRP in the data.

Head-to-Head Benchmarks

The database records no direct head-to-head benchmark results for these two GPUs, and neither has individual benchmark scores or average scores. The wins counters are both zero. However, the specification data allows a computed comparison across several key metrics.

In FP32 compute, the NVIDIA N1 20SM delivers 12.01 TFLOPS, which is 95.4% higher than the Intel Arc Pro B370's 6.144 TFLOPS. This is the most significant compute advantage in the comparison. The texture rate difference is even larger: the NVIDIA part achieves 375.4 GTexel/s versus 96.00 GTexel/s on the Intel part, a 291% advantage. This stems from the 160 TMUs versus 40 TMUs. The pixel rate favors NVIDIA by 17.3%, at 56.30 GPixel/s versus 48.00 GPixel/s.

The memory bandwidth comparison is stark. The NVIDIA N1 20SM has 273.2 GB/s dedicated bandwidth, while the Intel Arc Pro B370's bandwidth is System Dependent, meaning it shares system memory and cannot be quantified in the same way. The 128 GB memory capacity on the NVIDIA part versus System Shared on Intel further separates the two in memory-bound workloads.

The Intel Arc Pro B370 wins on clock speed. Its boost clock of 2400 MHz is 2.3% higher than the NVIDIA's 2346 MHz, and its base clock of 300 MHz is far lower than the NVIDIA's 741 MHz, indicating different power and clocking strategies. The Intel part also has a clear advantage in API support: DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4 versus none listed on the NVIDIA part.

In FP16, the Intel part reaches 12.29 TFLOPS with a 2:1 ratio, slightly higher than the NVIDIA part's 12.01 TFLOPS at 1:1. This means the Intel part processes FP16 at a faster rate than its FP32, while the NVIDIA part has identical FP16 and FP32 rates. For workloads using FP16, the Intel part has a 2.3% advantage in raw throughput.

Where Each One Wins

The NVIDIA N1 20SM wins in every raw throughput category except FP16 and boost clock. Its 2560 shading units, 160 TMUs, and 24 ROPs give it dominant texture and pixel fill rates. The 12.01 TFLOPS FP32 and 12.01 TFLOPS FP16 (1:1) make it the stronger compute device for general-purpose and AI workloads, especially with 80 tensor cores available. The 128 GB LPDDR5X memory with 273.2 GB/s bandwidth makes it suitable for large datasets and memory-intensive applications. The PCIe 5.0 x16 interface provides a high-bandwidth connection to the host system.

The Intel Arc Pro B370 wins in graphics API compatibility and power efficiency. It is the only one of the two with DirectX 12 Ultimate support, which is required for modern Windows gaming and graphics applications. It also supports OpenGL 4.6 and Vulkan 1.4, making it a functional general-purpose graphics solution. Its 25 W TDP is a recorded figure, while the NVIDIA part's TDP is unknown, so the Intel part is the only one with a confirmed low-power profile. The Intel part also has a higher boost clock at 2400 MHz and a faster FP16 rate at 12.29 TFLOPS with a 2:1 ratio. Its 10 RT cores provide ray tracing capability, though half the count of the NVIDIA part.

For portable devices, the Intel Arc Pro B370 with its IGP bus interface and Portable Device Dependent display outputs is positioned for integrated use in mobile systems. The NVIDIA N1 20SM, also an IGP but with a PCIe 5.0 x16 interface and a single HDMI output, appears suited for embedded or specialized systems where compute density and memory capacity matter more than graphics API support. The data shows a clear division: NVIDIA for compute and memory bandwidth, Intel for graphics rendering and standard API support.