Intel Arc B370 vs NVIDIA B200 SXM6 Comparison

Head-to-Head Benchmarks

The database contains only one recorded benchmark score for the Intel Arc B370: 3DMark Steel Nomad DX12, where it scores 1184 points. This places it in the 5th percentile of all GPUs in the database. The NVIDIA B200 SXM6 has no recorded benchmark entries, producing an average benchmark score of 0 and a 50th percentile ranking. A direct head-to-head comparison is therefore impossible from measured data alone.

The Arc B370's nearest rivals in the database show how tightly clustered its performance is. The ATI Mobility Radeon HD 5570 scores 1186, a delta of -0.2% relative to the Arc B370. The ATI Radeon HD 5770 scores 1190, a -0.5% delta. The AMD Radeon HD 7650M scores 1192, a -0.7% delta. The AMD FirePro M2000 scores 1168, a +1.4% delta. These deltas indicate the Arc B370 sits within roughly 1.5 percentage points of all four nearest rivals, meaning its measured performance is effectively comparable to a group of older discrete and mobile GPUs.

Because the B200 SXM6 has no benchmark scores, the delta between the two products cannot be quantified. The Arc B370's single result represents its entire measured performance profile, while the B200 SXM6 represents none. The data shows the Arc B370 is positioned as a low-power integrated graphics solution aimed at portable devices, while the B200 SXM6 is a server-grade accelerator with no display output and no gaming-oriented benchmark data.

Where Each One Wins

The Arc B370 wins in any scenario requiring integrated graphics with display capability. Its display outputs are marked as "Portable Device Dependent," indicating it is designed for laptops or similar portable hardware where the display is built into the device. It supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, making it suitable for modern gaming APIs on such devices. Its 25 W TDP and lack of power connectors further confirm its role in power-constrained portable systems.

The B200 SXM6 wins in raw compute throughput. Its FP32 performance is 69.34 TFLOPS, more than 11 times the Arc B370's 6.144 TFLOPS. Its FP16 performance is also 69.34 TFLOPS with a 1:1 ratio, while the Arc B370 delivers 12.29 TFLOPS FP16 at a 2:1 ratio. The B200 SXM6 has 18944 shading units versus 1280, 592 texture mapping units versus 40, and 592 tensor cores versus none on the Arc B370. The B200 SXM6 also offers 180 GB of HBM3e memory with 8.19 TB/s bandwidth over an 8192-bit bus, whereas the Arc B370 uses system-shared memory with bandwidth described as "System Dependent."

The B200 SXM6 is built for server workloads. It has no display outputs, no DirectX, OpenGL, or Vulkan support, and uses an SXM module form factor. The Arc B370 is built for client devices. Its pixel rate of 48.00 GPixel/s slightly exceeds the B200 SXM6's 43.92 GPixel/s, but its texture rate of 96.00 GTexel/s is dramatically lower than the B200 SXM6's 1,083.4 GTexel/s.

Architecture Differences

The Intel Arc B370 uses the Panther Lake chip with the Xe3-LPG architecture, belonging to the Arc Graphics-M (Panther Lake) generation. It is fabricated on a 3 nm process at Intel. The NVIDIA B200 SXM6 uses the GB100 chip with the Blackwell architecture, belonging to the Server Blackwell (Bxx) generation. It is fabricated on a 5 nm process at TSMC. The B200 SXM6 has 208,000 million transistors on a 1628 mm² die, giving a transistor density of 127.8 million transistors per square millimeter. The Arc B370's transistor count and die size are listed as unknown.

The Arc B370 has 1280 shading units, 40 TMUs, 20 ROPs, and 10 ray tracing cores. The B200 SXM6 has 18944 shading units, 592 TMUs, 24 ROPs, and 592 tensor cores, with no ray tracing cores listed. The Arc B370's ray tracing capability comes from its 10 dedicated RT cores, while the B200 SXM6 relies on tensor cores for its compute focus.

Clock behavior differs substantially. The Arc B370 runs at a 300 MHz base clock and 2400 MHz boost clock. The B200 SXM6 runs at a 120 MHz base clock and 1830 MHz boost clock. Memory clocking also differs: the Arc B370 uses system-shared memory with no dedicated clock, while the B200 SXM6 uses 2000 MHz memory with 8 Gbps effective speed.

The B200 SXM6 has a 1000 W TDP, a suggested power supply of 1400 W, and uses a PCIe 6.0 x16 bus interface. The Arc B370 has a 25 W TDP, no power connectors, and uses an IGP bus interface. The B200 SXM6's predecessor is Server Hopper and its successor is Server Rubin, while the Arc B370 has no listed predecessor or successor.

FAQ

Q: Which GPU has a higher FP32 compute throughput?

A: The NVIDIA B200 SXM6 delivers 69.34 TFLOPS FP32, compared to the Intel Arc B370's 6.144 TFLOPS. The B200 SXM6 is over 11 times faster in raw FP32 performance.

Q: Can the NVIDIA B200 SXM6 output video to a display?

A: No. The B200 SXM6 lists "No outputs" for display connections and has no DirectX, OpenGL, or Vulkan API support. It is designed for server compute workloads only.

Q: What is the memory configuration of each GPU?

A: The Arc B370 uses system-shared memory with system-dependent bandwidth. The B200 SXM6 has 180 GB of HBM3e memory with an 8192-bit bus and 8.19 TB/s bandwidth.

Q: Which GPU supports ray tracing?

A: The Intel Arc B370 has 10 dedicated ray tracing cores and supports DirectX 12 Ultimate (12_2). The NVIDIA B200 SXM6 has no listed ray tracing cores.

Q: What is the power requirement difference?

A: The Arc B370 has a 25 W TDP and requires no power connectors. The B200 SXM6 has a 1000 W TDP and requires a suggested power supply of 1400 W.

Q: How does the Arc B370's benchmark score compare to its nearest rivals?

A: The Arc B370 scores 1184 in 3DMark Steel Nomad DX12. Its nearest rivals score 1186 (ATI Mobility Radeon HD 5570, -0.2%), 1190 (ATI Radeon HD 5770, -0.5%), 1192 (AMD Radeon HD 7650M, -0.7%), and 1168 (AMD FirePro M2000, +1.4%).

The Verdict

The data shows two products with entirely different purposes. The Intel Arc B370 is an integrated graphics processor for portable devices, evidenced by its IGP bus interface, 25 W TDP, system-shared memory, and portable-device-dependent display outputs. Its single benchmark score of 1184 places it in the 5th percentile of all GPUs, and its nearest rivals are all older discrete or mobile GPUs from the HD 5000 and 7000 series era. This indicates modest gaming capability suitable for light workloads on laptops.

The NVIDIA B200 SXM6 is a server accelerator with no display capability, no consumer API support, and a 1000 W TDP. Its 69.34 TFLOPS FP32, 69.34 TFLOPS FP16, 180 GB of HBM3e memory, and 8.19 TB/s bandwidth position it for high-performance compute tasks such as AI training or scientific simulation. Its 50th percentile ranking in the database is based on its presence rather than measured benchmarks, since no benchmark scores are recorded.

The Arc B370 should be chosen for portable devices where integrated graphics with modern API support are needed. The B200 SXM6 should be chosen for server installations requiring massive compute throughput and memory bandwidth. The two products do not compete in any meaningful way, and the benchmark data confirms this separation.

Specification Differences

| Specification | Intel Arc B370 | NVIDIA B200 SXM6 |

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

| Chip | Panther Lake | GB100 |

| Architecture | Xe3-LPG | Blackwell |

| Generation | Arc Graphics-M (Panther Lake) | Server Blackwell (Bxx) |

| Process Node | 3 nm | 5 nm |

| Foundry | Intel | TSMC |

| Transistors | unknown | 208,000 million |

| Die Size | unknown | 1628 mm² |

| Transistor Density | null | 127.8M / mm² |

| Base Clock | 300 MHz | 120 MHz |

| Boost Clock | 2400 MHz | 1830 MHz |

| Memory Size | System Shared | 180 GB |

| Memory Type | System Shared | HBM3e |

| Memory Bus Width | System Shared | 8192 bit |

| Memory Bandwidth | System Dependent | 8.19 TB/s |

| Shading Units | 1280 | 18944 |

| TMUs | 40 | 592 |

| ROPs | 20 | 24 |

| RT Cores | 10 | null |

| Tensor Cores | null | 592 |

| Pixel Rate | 48.00 GPixel/s | 43.92 GPixel/s |

| Texture Rate | 96.00 GTexel/s | 1,083.4 GTexel/s |

| FP32 | 6.144 TFLOPS | 69.34 TFLOPS |

| FP16 | 12.29 TFLOPS (2:1) | 69.34 TFLOPS (1:1) |

| TDP | 25 W | 1000 W |

| Slot Width | IGP | SXM Module |

| Power Connectors | None | null |

| Suggested PSU | null | 1400 W |

| Bus Interface | IGP | PCIe 6.0 x16 |

| Display Outputs | Portable Device Dependent | No outputs |

| DirectX | 12 Ultimate (12_2) | N/A |

| OpenGL | 4.6 | N/A |

| Vulkan | 1.4 | N/A |

| Release Date | 2026-01-26 | 2024-10-31 |

| Predecessor | null | Server Hopper |

| Successor | null | Server Rubin |

| Launch MSRP | null | 34,999 USD |

| Percentile vs All GPUs | 5 | 50 |

| Avg Benchmark Score | 1184 | 0 |