Intel Arc 130T Mobile vs NVIDIA B200 SXM6 Comparison

Head-to-Head Benchmarks

The recorded data for the Intel Arc 130T Mobile and the NVIDIA B200 SXM6 contains no direct head-to-head benchmark scores, no wins for either product, and no nearest rival comparisons. The database shows a percentile versus all GPUs of 50 for both parts, with an average benchmark score of 0 for each. This absence of measured results means the comparison must rest entirely on the specification sheets and architectural characteristics.

The Intel Arc 130T Mobile delivers 3.942 TFLOPS of FP32 compute, while the NVIDIA B200 SXM6 reaches 69.34 TFLOPS, a 17.6 times difference in raw single-precision throughput. In FP16, the Intel part lists 7.885 TFLOPS at a 2:1 ratio, whereas the B200 lists 69.34 TFLOPS at a 1:1 ratio, meaning the NVIDIA part does not rely on a reduced-precision shortcut to achieve its figure. The texture rate favors the B200 at 1,083.4 GTexel/s versus 123.2 GTexel/s for the Intel GPU, a factor of roughly 8.8. The pixel rate, however, goes the other direction: Intel records 61.60 GPixel/s, while NVIDIA records 43.92 GPixel/s, giving the Arc a 40% lead in fill rate.

Memory bandwidth is where the separation becomes extreme. The B200 SXM6 uses 180 GB of HBM3e over an 8192-bit bus, producing 8.19 TB/s of bandwidth. The Arc 130T Mobile uses system shared memory with bandwidth described as "System Dependent," so no fixed number exists to compare. Clock behavior also differs sharply: the Arc has a 300 MHz base and 2200 MHz boost, while the B200 has a 120 MHz base and 1830 MHz boost. The B200's lower clocks but vastly higher core count (18944 shading units versus 896) explain its compute dominance.

The B200 SXM6 shows a launch MSRP of 34,999 USD, while the Arc 130T Mobile has no recorded launch price. The power envelope differs by a factor of 28.6: the B200 is rated at 1000 W with a suggested PSU of 1400 W, whereas the Arc fits within a 35 W TDP and uses no external power connectors. The Arc is an integrated graphics processor (IGP) with a slot width of IGP, while the B200 is a discrete SXM Module with a PCIe 6.0 x16 interface.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The NVIDIA B200 SXM6 records 69.34 TFLOPS FP32, which is 17.6 times the 3.942 TFLOPS of the Intel Arc 130T Mobile.

Q: How do the memory configurations compare?

A: The B200 SXM6 uses 180 GB of HBM3e on an 8192-bit bus with 8.19 TB/s bandwidth. The Arc 130T Mobile relies on system shared memory with no fixed size, type, bus width, or bandwidth; the database lists bandwidth as "System Dependent."

Q: What are the thermal design power ratings?

A: The Intel Arc 130T Mobile has a TDP of 35 W. The NVIDIA B200 SXM6 has a TDP of 1000 W and suggests a 1400 W power supply.

Q: Which GPU supports DirectX?

A: Only the Intel Arc 130T Mobile lists API support: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The NVIDIA B200 SXM6 records N/A for DirectX, OpenGL, and Vulkan, indicating no display or consumer graphics API support.

Q: What is the release timeline for these products?

A: The Intel Arc 130T Mobile released on 2025-01-12, and the NVIDIA B200 SXM6 released on 2024-10-31. Both are listed as Active in production status.

Q: Do these GPUs have tensor cores?

A: The B200 SXM6 includes 592 tensor cores. The Arc 130T Mobile has no tensor core count listed in the database.

The Verdict

The data indicates two products with no overlapping use cases. The Arc 130T Mobile is a low-power integrated processor for portable devices, with a 35 W TDP, system shared memory, and display outputs described as "Portable Device Dependent." It supports DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4, making it a candidate for consumer graphics workloads on a laptop or compact system.

The B200 SXM6 is a server module with no display outputs, no consumer API support, and a 1000 W power draw. Its 69.34 TFLOPS FP32, 8.19 TB/s memory bandwidth, and 592 tensor cores position it for compute-heavy server tasks. The launch MSRP of 34,999 USD places it in a professional data center segment. The 35 W integrated part and the 1000 W server module serve different buyers, and the benchmark data does not provide any cross-applicable scores to suggest otherwise.

Specification Differences

The two GPUs differ on nearly every measurable specification. Process node is the same (5 nm, TSMC foundry) for both. Transistor count is unknown for Intel, while NVIDIA lists 208,000 million transistors on a 1628 mm² die with a density of 127.8M per mm². The Intel die size is unknown.

Base clocks: 300 MHz (Intel) versus 120 MHz (NVIDIA). Boost clocks: 2200 MHz (Intel) versus 1830 MHz (NVIDIA). Memory clock: "System Shared" for Intel versus 2000 MHz with 8 Gbps effective for NVIDIA. Memory size: "System Shared" for Intel versus 180 GB for NVIDIA. Memory type: "System Shared" versus HBM3e. Bus width: "System Shared" versus 8192 bit. Bandwidth: "System Dependent" versus 8.19 TB/s.

Shading units: 896 versus 18944. Texture mapping units: 56 versus 592. Raster output units: 28 versus 24. Ray tracing cores: 7 for Intel, none listed for NVIDIA. Tensor cores: none listed for Intel, 592 for NVIDIA. Pixel rate: 61.60 GPixel/s versus 43.92 GPixel/s. Texture rate: 123.2 GTexel/s versus 1,083.4 GTexel/s. FP32: 3.942 TFLOPS versus 69.34 TFLOPS. FP16: 7.885 TFLOPS (2:1) versus 69.34 TFLOPS (1:1). TDP: 35 W versus 1000 W. Slot width: IGP versus SXM Module. Bus interface: IGP versus PCIe 6.0 x16. Display outputs: "Portable Device Dependent" versus "No outputs." APIs: Intel lists DirectX 12 Ultimate, OpenGL 4.6, Vulkan 1.4; NVIDIA lists N/A for all three.

Architecture Differences

The Intel Arc 130T Mobile uses the Arrow Lake-H chip with Xe-LPG+ architecture, part of the Arc Graphics-M (Arrow Lake) generation. Its predecessor is listed as HD Graphics-M. The NVIDIA B200 SXM6 uses the GB100 chip with Blackwell architecture, part of the Server Blackwell (Bxx) generation, with predecessor Server Hopper and successor Server Rubin.

The Intel architecture includes 7 ray tracing cores, which the NVIDIA part does not list. The NVIDIA architecture includes 592 tensor cores, which the Intel part does not list. The Intel GPU provides shading units, TMUs, and ROPs in a 896/56/28 configuration, while NVIDIA uses 18944/592/24. The NVIDIA ROP count is lower than Intel's, which aligns with its lower pixel rate despite massive compute superiority.

The Intel part is an integrated design (IGP slot width, system shared memory, no power connectors), while the NVIDIA part is a modular server component (SXM Module, dedicated HBM3e, PCIe 6.0 x16). The process nodes match at 5 nm from TSMC, but the transistor budgets differ enormously, with NVIDIA packing over 200 billion transistors into a 1628 mm² die. The Intel part has no recorded transistor count, die size, or density. The memory architecture separates them fully: Intel uses shared system memory with dependent bandwidth, while NVIDIA has 180 GB of HBM3e at 8.19 TB/s.

Where Each One Wins

The Intel Arc 130T Mobile wins in pixel rate, posting 61.60 GPixel/s against 43.92 GPixel/s for the B200 SXM6. This indicates a fill-rate advantage that could matter in rasterization-focused rendering tasks. The Intel part also wins on power efficiency in absolute terms, drawing 35 W versus 1000 W, and it supports consumer graphics APIs (DirectX 12 Ultimate, OpenGL 4.6, Vulkan 1.4) that the NVIDIA server module lacks. The Arc has display outputs, making it suitable for portable devices, and its 7 ray tracing cores provide hardware RT support that the B200 does not list.

The NVIDIA B200 SXM6 wins on every compute-heavy metric. Its FP32 throughput of 69.34 TFLOPS is 17.6 times higher than the Intel part. Its FP16 performance matches its FP32 at 69.34 TFLOPS, meaning no precision trade-off. Texture rate reaches 1,083.4 GTexel/s, roughly 8.8 times the Intel figure. Memory bandwidth of 8.19 TB/s far exceeds the system-dependent bandwidth of the Arc. The 592 tensor cores and 180 GB HBM3e capacity target AI training and inference workloads. The 8192-bit memory bus and 1000 W power envelope indicate a sustained high-throughput compute platform.

The use-case split is clear from the data. The Arc 130T Mobile suits integrated graphics in portable systems where low power (35 W) and API support for consumer software matter. The B200 SXM6 suits server deployments where memory capacity, bandwidth, tensor throughput, and raw FP32/FP16 compute are the priority, with no need for display output or consumer API compatibility. The database shows no overlapping benchmark results, so each product wins in its respective domain by specification alone.