AMD Radeon RX 6600 LE vs Intel Arc B370 Comparison

AMD Radeon RX 6600 LE versus Intel Arc B370 is a comparison of two fundamentally different GPU classes. The RX 6600 LE is a discrete, 7 nm desktop graphics card built on RDNA 2.0, while the Arc B370 is a 3 nm integrated GPU within Intel's Panther Lake mobile processor. The database shows a massive performance gulf between the two, defined by distinct architectural priorities, memory strategies, and power envelopes.

Head-to-Head Benchmarks

The recorded benchmark data shows a decisive performance advantage for the AMD Radeon RX 6600 LE. The RX 6600 LE achieves an average benchmark score of 70,829, which places it in the 91st percentile of all GPUs in the database. The Intel Arc B370, in contrast, has an average benchmark score of 1,184, placing it in the 5th percentile. This represents a staggering difference in overall compute capability, with the AMD part delivering roughly 60 times the average score of the Intel integrated solution.

The RX 6600 LE's benchmark results are consistent across both OpenCL and Vulkan APIs. It scores 69,229 in Geekbench OpenCL and 72,428 in Geekbench Vulkan. The Arc B370's only recorded benchmark is a 3DMark Steel Nomad DX12 score of 1,184. While these tests are not directly comparable due to different workloads and APIs, the percentile rankings provide a clear picture: the RX 6600 LE is a high-performing discrete GPU, while the Arc B370 is an entry-level integrated part.

Looking at the nearest rivals in the database further contextualizes the RX 6600 LE's standing. Its closest competitors include the NVIDIA RTX A3000 Mobile with an average score of 70,140, which is 1% behind the RX 6600 LE, and the AMD Radeon RX 6650M with an average score of 71,768, which is 1.3% ahead. The RX 6600 LE also edges out the NVIDIA Quadro P6000 (69,986, 1.2% behind) and the AMD Radeon Pro WX 8200 (69,870, 1.4% behind). These margins are narrow, indicating that the RX 6600 LE sits in a competitive tier among discrete mobile and workstation GPUs.

The Arc B370's nearest rivals are all much older, lower-performing parts. The ATI Mobility Radeon HD 5570 scores 1,186, which is 0.2% ahead of the Arc B370, while the ATI Radeon HD 5770 scores 1,190, 0.5% ahead. The AMD Radeon HD 7650M scores 1,192 (0.7% ahead), and the AMD FirePro M2000 scores 1,168 (1.4% behind). The Arc B370's performance is essentially on par with these legacy GPUs from over a decade ago, highlighting its position as a basic integrated graphics solution.

Benchmark results indicate that the RX 6600 LE is not just faster, it is in a completely different performance class. The data shows no overlap in scores; the RX 6600 LE's lowest recorded result (69,229) is still nearly 58 times higher than the Arc B370's only recorded score. This is a comparison of a dedicated gaming and workstation GPU against a power-efficient integrated graphics unit.

Architecture Differences

The two GPUs are built on entirely different architectures and process nodes. The AMD Radeon RX 6600 LE uses the Navi 23 chip based on the RDNA 2.0 architecture, fabricated on a 7 nm process at TSMC. It contains 11,060 million transistors on a 237 mm² die, resulting in a transistor density of 46.7 million per square millimeter. The Intel Arc B370 uses the Panther Lake chip based on the Xe3-LPG architecture, fabricated on a 3 nm process at Intel's own foundry. Its transistor count and die size are listed as unknown in the database.

The RX 6600 LE is a fully discrete card with its own dedicated memory. It features 8 GB of GDDR6 memory on a 128-bit bus, providing a bandwidth of 224.0 GB/s. The Arc B370, by contrast, uses System Shared memory, meaning its memory size, type, bus width, and bandwidth are all system dependent. This is a fundamental architectural difference: the RX 6600 LE has dedicated high-speed VRAM, while the Arc B370 relies on the host system's main memory.

Compute unit configurations differ significantly. The RX 6600 LE has 1,792 shading units, 112 texture mapping units (TMUs), 64 render output units (ROPs), and 28 ray tracing cores. The Arc B370 has 1,280 shading units, 40 TMUs, 20 ROPs, and 10 ray tracing cores. The RX 6600 LE has 40% more shading units, 180% more TMUs, 220% more ROPs, and 180% more ray tracing cores.

Clock speeds also diverge. The RX 6600 LE has a base clock of 1,626 MHz, a boost clock of 2,495 MHz, and a game clock of 2,045 MHz. Its memory runs at 1,750 MHz with 14 Gbps effective speed. The Arc B370 has a much lower base clock of 300 MHz but a boost clock of 2,400 MHz, close to the RX 6600 LE's boost. However, the Arc B370's memory clock is listed as System Shared, again indicating its dependence on the host system.

The RX 6600 LE's architecture yields far higher throughput rates. It achieves a pixel rate of 159.7 GPixel/s and a texture rate of 279.4 GTexel/s. The Arc B370 achieves only 48.00 GPixel/s and 96.00 GTexel/s. In raw FP32 compute, the RX 6600 LE delivers 8.942 TFLOPS, while the Arc B370 delivers 6.144 TFLOPS. FP16 performance follows the same pattern: 17.88 TFLOPS for the RX 6600 LE versus 12.29 TFLOPS for the Arc B370, both at a 2:1 ratio.

Power and physical design are also fundamentally different. The RX 6600 LE has a TDP of 132 W, requires a 1x 8-pin power connector, and a suggested 300 W power supply. It is a dual-slot card measuring 190 mm in length, 110 mm in height, and 40 mm in width. The Arc B370 has a TDP of only 25 W, uses no power connectors, and is classified as an IGP (integrated graphics processor), meaning it has no physical dimensions listed and its bus interface is IGP rather than PCIe.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The AMD Radeon RX 6600 LE has a significantly higher average benchmark score of 70,829 compared to the Intel Arc B370's 1,184, placing it in the 91st percentile versus the 5th percentile.

Q: What is the difference in memory configuration?

A: The RX 6600 LE uses 8 GB of dedicated GDDR6 memory on a 128-bit bus with 224.0 GB/s bandwidth. The Arc B370 uses System Shared memory, meaning its size, type, bus width, and bandwidth are all system dependent.

Q: How do the process nodes compare?

A: The RX 6600 LE is built on a 7 nm process at TSMC, while the Arc B370 is built on a 3 nm process at Intel. The RX 6600 LE has 11,060 million transistors on a 237 mm² die, while the Arc B370's transistor count and die size are unknown.

Q: Which GPU has more shading units?

A: The RX 6600 LE has 1,792 shading units, which is 40% more than the Arc B370's 1,280 shading units. The RX 6600 LE also has 112 TMUs versus 40, 64 ROPs versus 20, and 28 ray tracing cores versus 10.

Q: What is the power consumption difference?

A: The RX 6600 LE has a TDP of 132 W and requires a 1x 8-pin power connector with a suggested 300 W power supply. The Arc B370 has a TDP of 25 W and uses no power connectors.

Q: What APIs are supported by both GPUs?

A: Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Specification Differences

| Specification | AMD Radeon RX 6600 LE | Intel Arc B370 |

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

| Process Node | 7 nm | 3 nm |

| Foundry | TSMC | Intel |

| Transistors | 11,060 million | Unknown |

| Die Size | 237 mm² | Unknown |

| Base Clock | 1626 MHz | 300 MHz |

| Boost Clock | 2495 MHz | 2400 MHz |

| Memory Size | 8 GB | System Shared |

| Memory Type | GDDR6 | System Shared |

| Memory Bus Width | 128 bit | System Shared |

| Memory Bandwidth | 224.0 GB/s | System Dependent |

| Shading Units | 1792 | 1280 |

| TMUs | 112 | 40 |

| ROPs | 64 | 20 |

| Ray Tracing Cores | 28 | 10 |

| Pixel Rate | 159.7 GPixel/s | 48.00 GPixel/s |

| Texture Rate | 279.4 GTexel/s | 96.00 GTexel/s |

| FP32 | 8.942 TFLOPS | 6.144 TFLOPS |

| FP16 | 17.88 TFLOPS (2:1) | 12.29 TFLOPS (2:1) |

| TDP | 132 W | 25 W |

| Slot Width | Dual-slot | IGP |

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

| Bus Interface | PCIe 4.0 x8 | IGP |

| Display Outputs | 1x HDMI 2.1, 3x DisplayPort 1.4a | Portable Device Dependent |

| Dimensions | 190 mm x 110 mm x 40 mm | None listed |

The Verdict

The data presents a clear verdict: the AMD Radeon RX 6600 LE is a vastly more capable GPU than the Intel Arc B370. The RX 6600 LE scores 70,829 on average, placing it in the 91st percentile of all GPUs, while the Arc B370 scores 1,184, in the 5th percentile. The RX 6600 LE has 8 GB of dedicated GDDR6 memory with 224.0 GB/s bandwidth, while the Arc B370 relies entirely on system shared memory. The RX 6600 LE delivers 8.942 TFLOPS of FP32 compute, 159.7 GPixel/s pixel rate, and 279.4 GTexel/s texture rate, all far exceeding the Arc B370's 6.144 TFLOPS, 48.00 GPixel/s, and 96.00 GTexel/s.

The Arc B370's advantage lies in its efficiency and integration. It consumes only 25 W of power versus the RX 6600 LE's 132 W, requires no power connectors, and is an IGP, meaning it is built into a processor and takes up no additional slot space. The RX 6600 LE needs a 1x 8-pin power connector, a suggested 300 W power supply, and occupies a dual-slot footprint measuring 190 mm by 110 mm by 40 mm.

For users selecting a discrete GPU for gaming, content creation, or workstation tasks, the RX 6600 LE is the clear choice based on benchmark results. Its nearest rivals, such as the NVIDIA RTX A3000 Mobile and AMD Radeon RX 6650M, are within 1.3% of its average score, confirming its competitive position among dedicated GPUs. For users requiring a low-power integrated solution for basic computing, the Arc B370 is the only option, but its performance places it alongside GPUs like the ATI Radeon HD 5770 and AMD Radeon HD 7650M, which are all within 0.7% of its score.

Where Each One Wins

The AMD Radeon RX 6600 LE wins decisively in raw performance across every measured metric. It has higher shading unit count (1,792 versus 1,280), more TMUs (112 versus 40), more ROPs (64 versus 20), and more ray tracing cores (28 versus 10). Its dedicated memory subsystem with 224.0 GB/s bandwidth provides a massive advantage over the Arc B370's system-dependent shared memory. In compute workloads, the RX 6600 LE's 8.942 TFLOPS FP32 and 17.88 TFLOPS FP16 performance more than double the Arc B370's output in some ratios. The RX 6600 LE's 91st percentile ranking versus the Arc B370's 5th percentile confirms that it wins in all performance-oriented scenarios.

The Intel Arc B370 wins in power efficiency and physical integration. Its 25 W TDP is less than one-fifth of the RX 6600 LE's 132 W. It needs no power connectors, no suggested power supply rating, and occupies no expansion slot as an IGP. Its 3 nm process node at Intel represents a more advanced manufacturing technology compared to the RX 6600 LE's 7 nm node at TSMC. The Arc B370's base clock of 300 MHz is lower, but its boost clock of 2,400 MHz is close to the RX 6600 LE's 2,495 MHz, indicating that it can reach competitive clock speeds when the workload demands it, though with far fewer compute resources behind it. For a portable device where power draw and space are the primary constraints, the Arc B370's integrated design is the preferred solution, but the recorded data shows its performance ceiling is fundamentally limited.