AMD Radeon RX 6600 LE vs Intel Arc B390 Comparison

Where Each One Wins

The recorded data separates these two GPUs into entirely different performance classes. The AMD Radeon RX 6600 LE holds an average benchmark score of 70,829 points, placing it in the 91st percentile of all GPUs in the database. The Intel Arc B390, by contrast, averages 1,482 points and sits in the 9th percentile. The AMD part wins every recorded performance category, though the two are measured with different test suites, so direct apples-to-apples comparisons are limited to what the database provides.

The RX 6600 LE shows two benchmark entries: a Geekbench OpenCL score of 69,229 and a Geekbench Vulkan score of 72,428. The Arc B390 has only one recorded test, a 3DMark Steel Nomad DX12 score of 1,482. Because the test suites do not overlap, the database does not list any head-to-head benchmark wins for either card; the wins field shows zero for both. The performance gap is nonetheless evident from the aggregate scores and from the nearest rival comparisons.

The RX 6600 LE's nearest rivals in the database include the NVIDIA RTX A3000 Mobile at 70,140 (1% behind), the NVIDIA Quadro P6000 at 69,986 (1.2% behind), and the AMD Radeon Pro WX 8200 at 69,870 (1.4% behind). The only rival ahead of it is the AMD Radeon RX 6650M at 71,768, which leads by 1.3%. These are tight margins, indicating the RX 6600 LE sits in a competitive band of mid-range performance.

The Arc B390's nearest rivals are far less capable. The NVIDIA GeForce GT 520MX at 1,463 trails by 1.3%, the NVIDIA GeForce 800M at 1,460 trails by 1.5%, the NVIDIA GeForce GT 625 OEM at 1,446 trails by 2.5%, and the NVIDIA GeForce GT 710 at 1,443 trails by 2.7%. The clustering of these scores within a few percentage points places the Arc B390 at the very bottom of the database's performance distribution, alongside decade-old entry-level parts.

Architecture Differences

The two GPUs come from different manufacturers, process nodes, and design philosophies. The RX 6600 LE uses the Navi 23 chip built on RDNA 2.0 architecture, fabricated by TSMC on a 7 nm process. The chip contains 11,060 million transistors on a 237 mm² die, yielding a transistor density of 46.7 million transistors per square millimeter. The Arc B390 uses the Panther Lake chip with Xe3-LPG architecture, fabricated by Intel on a 3 nm process; its transistor count and die size are not recorded in the database.

The RX 6600 LE is a discrete add-in card with a dual-slot cooler, a single 8-pin power connector, and a suggested PSU of 300 W. Its TDP is 132 W. The Arc B390 is an integrated graphics processor (IGP) with no power connectors, no slot width beyond IGP designation, and a TDP of 80 W. This fundamental difference explains much of the performance disparity: the AMD part draws substantially more power and uses dedicated memory, while the Intel part shares system resources.

Memory configurations diverge sharply. The RX 6600 LE has 8 GB of GDDR6 on a 128-bit bus, delivering 224.0 GB/s of bandwidth. The Arc B390 uses system shared memory, with its bus width and size listed as system dependent. Its bandwidth is likewise system dependent, meaning no fixed figure exists in the database.

Compute resources also differ. The RX 6600 LE has 1,792 shading units, 112 texture mapping units, 64 ROPs, and 28 ray tracing cores. The Arc B390 has 1,536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores. The AMD card provides more of every processing unit category. Pixel fill rate for the RX 6600 LE is 159.7 GPixel/s versus 60.00 GPixel/s for the Arc B390. Texture fill rate is 279.4 GTexel/s versus 120.0 GTexel/s. FP32 throughput is 8.942 TFLOPS versus 7.680 TFLOPS, and FP16 throughput is 17.88 TFLOPS versus 15.36 TFLOPS, both at a 2:1 ratio.

Clock behavior differs in structure. The RX 6600 LE has a base clock of 1626 MHz, a boost clock of 2495 MHz, and a game clock of 2045 MHz. Its memory runs at 1750 MHz with 14 Gbps effective. The Arc B390 has a base clock of 300 MHz and a boost clock of 2500 MHz, but no game clock and no dedicated memory clock. The integration into a mobile processor explains the low base clock and the reliance on shared memory.

Head-to-Head Benchmarks

The database contains no overlapping benchmark entries for these two GPUs, so a direct test-by-test comparison is not possible from recorded measurements. What the data does provide is the aggregate average score and the percentile placement, which together establish the performance hierarchy.

The RX 6600 LE averages 70,829 points across its two Geekbench entries. The Arc B390 averages 1,482 points from its single 3DMark entry. Expressing the difference, the RX 6600 LE's average is roughly 47.8 times higher than the Arc B390's average. This is not a marginal gap; it spans nearly the entire range of the database's GPU performance distribution, from the 91st percentile down to the 9th.

Within its own benchmark results, the RX 6600 LE scores higher in Vulkan than in OpenCL. The Vulkan result of 72,428 exceeds the OpenCL result of 69,229 by 3,199 points, a 4.6% advantage. This suggests the RDNA 2.0 architecture responds well to the lower-level Vulkan API in the recorded Geekbench tests.

The Arc B390's single benchmark score of 1,482 places it fractionally ahead of the NVIDIA GeForce GT 520MX, which scores 1,463. The delta is 1.3%, a small margin that leaves the Arc B390 at the edge of the database's lowest performance tier. Its other nearest rivals, the GeForce 800M at 1,460, the GT 625 OEM at 1,446, and the GT 710 at 1,443, are all within 2.7% behind.

The RX 6600 LE's nearest rival comparison shows a much tighter competitive field. The RTX A3000 Mobile is only 1% behind, the Quadro P6000 is 1.2% behind, and the Radeon Pro WX 8200 is 1.4% behind. Only the Radeon RX 6650M surpasses it, and by just 1.3%. The RX 6600 LE is thus a mid-pack performer in a dense cluster of similar GPUs, whereas the Arc B390 is near the bottom of a sparse, low-performance cluster.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon RX 6600 LE averages 70,829 points, while the Intel Arc B390 averages 1,482 points.

Q: What percentile does each GPU occupy in the database?

A: The RX 6600 LE is in the 91st percentile of all GPUs. The Arc B390 is in the 9th percentile.

Q: How do the nearest rivals compare for each GPU?

A: The RX 6600 LE's closest rival is the AMD Radeon RX 6650M, which leads by 1.3%; the RTX A3000 Mobile trails by 1%. The Arc B390's closest rival is the NVIDIA GeForce GT 520MX, which trails by 1.3%.

Q: What memory does each GPU use?

A: The RX 6600 LE has 8 GB of GDDR6 on a 128-bit bus with 224.0 GB/s bandwidth. The Arc B390 uses system shared memory with system dependent bandwidth.

Q: What is the TDP difference between the two?

A: The RX 6600 LE has a TDP of 132 W with a suggested PSU of 300 W. The Arc B390 has a TDP of 80 W and no suggested PSU recorded.

Q: Do the two GPUs support the same APIs?

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

The Verdict

The recorded data supports a clear separation of roles. The AMD Radeon RX 6600 LE is a discrete, dual-slot graphics card with dedicated 8 GB GDDR6 memory, 1,792 shading units, and an average score in the 91st percentile. It competes within a tight band of mid-range GPUs, with all nearest rivals within 1.4% of its average score. Its higher TDP of 132 W and its 8-pin power connector indicate a conventional add-in card design intended for desktop systems with a 300 W PSU.

The Intel Arc B390 is an integrated GPU with 1,536 shading units, system shared memory, and no power connectors. Its 80 W TDP and IGP slot width indicate it is designed for portable or integrated platforms. Its average score of 1,482 places it in the 9th percentile, alongside the NVIDIA GeForce GT 710 and similar low-end parts. No benchmark data suggests it can approach the RX 6600 LE's performance level.

The database shows the RX 6600 LE as the stronger GPU by every recorded metric: shading units, TMUs, ROPs, ray tracing cores, pixel rate, texture rate, FP32, FP16, and average benchmark score. The Arc B390's advantages are limited to its lower 80 W TDP, its smaller 3 nm process node, and its integrated form factor that requires no separate power connection. For workloads that fit on a discrete card with dedicated memory, the RX 6600 LE is the higher-performance option. For a low-power integrated solution, the Arc B390 is the only one of the two that fits that role.

Specification Differences

| Specification | AMD Radeon RX 6600 LE | Intel Arc B390 |

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

| Architecture | RDNA 2.0 | Xe3-LPG |

| Process node | 7 nm | 3 nm |

| Foundry | TSMC | Intel |

| Transistors | 11,060 million | unknown |

| Die size | 237 mm² | unknown |

| Transistor density | 46.7M / mm² | null |

| Base clock | 1626 MHz | 300 MHz |

| Boost clock | 2495 MHz | 2500 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 | 1536 |

| TMUs | 112 | 48 |

| ROPs | 64 | 24 |

| Ray tracing cores | 28 | 12 |

| Pixel rate | 159.7 GPixel/s | 60.00 GPixel/s |

| Texture rate | 279.4 GTexel/s | 120.0 GTexel/s |

| FP32 | 8.942 TFLOPS | 7.680 TFLOPS |

| FP16 | 17.88 TFLOPS (2:1) | 15.36 TFLOPS (2:1) |

| TDP | 132 W | 80 W |

| Slot width | Dual-slot | IGP |

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

| Suggested PSU | 300 W | null |

| Bus interface | PCIe 4.0 x8 | IGP |

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

| Release date | 2023-12-07 | 2026-01-26 |

| Average benchmark score | 70829 | 1482 |

| Percentile vs all GPUs | 91 | 9 |