AMD Radeon RX 7900M vs Intel Arc B390 Comparison

The Verdict

The AMD Radeon RX 7900M and Intel Arc B390 are in completely different performance classes. The data shows a 183.5% advantage for the RX 7900M in the single head-to-head benchmark, the 3DMark Steel Nomad DX12 test, with scores of 4201 versus 1482. The RX 7900M sits at the 94th percentile among all GPUs, while the Intel Arc B390 sits at the 9th percentile.

The RX 7900M is the clear choice for anyone needing substantial graphics compute in a portable device. Its average benchmark score of 97487 positions it near workstation-class hardware, with rivals like the AMD Radeon Pro VII at 97131 (0.4% behind) and the NVIDIA Quadro RTX 6000 at 101872 (4.3% ahead). The Intel Arc B390, by contrast, averages only 1482, placing it alongside legacy entry-level parts such as the NVIDIA GeForce GT 520MX at 1463 (1.3% behind) and the NVIDIA GeForce 800M at 1460 (1.5% behind).

For users who need playable modern gaming or GPU-accelerated content creation, the RX 7900M is the only viable option between these two. The Arc B390 would serve basic display output and light workloads, but benchmark results indicate it cannot handle demanding DX12 titles at competitive performance levels. The RX 7900M delivers roughly three times the raw rasterization score, and that gap translates directly to real-world capability differences.

Architecture Differences

The two GPUs come from different manufacturers, process nodes, and design generations. The AMD Radeon RX 7900M uses the Navi 31 chip with RDNA 3.0 architecture, codenamed Plum Bonito, and belongs to the Navi Mobile (RX 7000M) generation. It is built on a 5 nm process at TSMC with 57,700 million transistors on a 529 mm² die, yielding a transistor density of 109.1M per mm².

The Intel Arc B390 uses the Panther Lake chip with Xe3-LPG architecture and belongs to the Arc Graphics-M (Panther Lake) generation. It is built on a 3 nm process at Intel, with transistor count and die size listed as unknown. This process node advantage for Intel does not translate into performance advantages, as the architectural differences dominate.

Core configurations differ dramatically. The RX 7900M features 4608 shading units, 288 texture mapping units, 192 raster output units, and 72 ray tracing cores. The Arc B390 has 1536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores. That means the RX 7900M has 3 times the shading units, 6 times the TMUs, 8 times the ROPs, and 6 times the ray tracing cores.

Clock behavior also differs. The RX 7900M runs at a base clock of 1825 MHz and boosts to 2090 MHz. The Arc B390 has a much lower base clock of 300 MHz but boosts higher to 2500 MHz. Despite the higher boost clock, the Arc B390's smaller core count limits its throughput. Memory architecture is another major divergence: the RX 7900M has 16 GB of GDDR6 on a 256-bit bus with 576.0 GB/s bandwidth, while the Arc B390 uses system shared memory with system dependent bandwidth.

Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both are integrated-style packages with IGP slot width and no power connectors, though their TDPs differ at 180 W for AMD and 80 W for Intel.

Head-to-Head Benchmarks

The only recorded head-to-head test is 3DMark Steel Nomad DX12. The AMD Radeon RX 7900M scores 4201, while the Intel Arc B390 scores 1482. The delta is 183.5%, meaning the RX 7900M outperforms the Arc B390 by nearly 2.8 times in this workload.

This single benchmark is a comprehensive rasterization test that stresses DX12 performance. The 183.5% lead is enormous and consistent with the underlying specifications. The RX 7900M's FP32 throughput of 38.52 TFLOPS compared to 7.680 TFLOPS for the Arc B390 explains most of this gap. The RX 7900M also produces 401.3 GPixel/s pixel fill rate versus 60.00 GPixel/s for the Arc B390, and 601.9 GTexel/s texture rate versus 120.0 GTexel/s.

The Arc B390's higher boost clock of 2500 MHz versus 2090 MHz cannot compensate for the core count disparity. With 1536 shading units versus 4608, the Arc B390 simply lacks the parallel execution resources needed for modern DX12 rendering. The RX 7900M also has 72 ray tracing cores compared to 12, giving it a substantial advantage in any ray-traced content as well.

In the broader benchmark context, the RX 7900M also recorded Geekbench OpenCL score of 129499 and Geekbench Vulkan score of 158760. No comparable scores exist for the Arc B390 in these tests, so direct comparison relies on the Steel Nomad result and the average benchmark scores of 97487 versus 1482.

FAQ

Q: Which GPU has the higher 3DMark Steel Nomad DX12 score?

A: The AMD Radeon RX 7900M scores 4201, which is 183.5% higher than the Intel Arc B390's 1482.

Q: What memory configuration does each GPU use?

A: The RX 7900M has 16 GB of GDDR6 on a 256-bit bus with 576.0 GB/s bandwidth. The Arc B390 uses system shared memory with system dependent bandwidth.

Q: How do the shading unit counts compare?

A: The RX 7900M has 4608 shading units, while the Arc B390 has 1536 shading units. The RX 7900M has exactly 3 times as many.

Q: What process nodes are used?

A: The RX 7900M is built on a 5 nm process at TSMC. The Arc B390 is built on a 3 nm process at Intel.

Q: Which GPU supports ray tracing?

A: Both support DirectX 12 Ultimate (12_2), which includes ray tracing. The RX 7900M has 72 ray tracing cores, while the Arc B390 has 12.

Q: Where does each GPU rank among all GPUs?

A: The RX 7900M is at the 94th percentile, while the Arc B390 is at the 9th percentile.

Where Each One Wins

AMD Radeon RX 7900M: The RX 7900M wins the only recorded head-to-head benchmark by 183.5%. Its 16 GB dedicated GDDR6 memory with 576.0 GB/s bandwidth makes it suitable for large textures, high-resolution rendering, and memory-intensive workloads. The 4608 shading units, 288 TMUs, and 192 ROPs provide the raw throughput needed for modern gaming and GPU compute. Its FP32 performance of 38.52 TFLOPS and FP16 of 77.05 TFLOPS (2:1) position it for content creation and scientific workloads. The 72 ray tracing cores enable hardware-accelerated ray tracing. The RX 7900M's 94th percentile ranking places it among the top tier of GPUs. Its rivals include the AMD Radeon Pro VII (0.4% lower average score), NVIDIA Quadro RTX 6000 (4.3% higher average score), AMD Radeon Instinct MI60 (5.4% lower), and NVIDIA RTX A4500 (6.3% lower). This places it in professional workstation territory.

Intel Arc B390: The Arc B390 wins no recorded head-to-head benchmarks. Its strengths lie in efficiency rather than performance. The 80 W TDP is less than half of the RX 7900M's 180 W, making it suitable for thin-and-light portable devices where power draw matters more than raw performance. The 3 nm process at Intel is more advanced than the 5 nm process at TSMC, though this does not yield performance benefits. The 2500 MHz boost clock is higher than the RX 7900M's 2090 MHz, but the smaller core configuration limits actual output. The Arc B390's 9th percentile ranking places it near entry-level legacy GPUs. Its rivals include the NVIDIA GeForce GT 520MX (1.3% higher average score), NVIDIA GeForce 800M (1.5% higher), NVIDIA GeForce GT 625 OEM (2.5% higher), and NVIDIA GeForce GT 710 (2.7% higher). This indicates the Arc B390 performs at a level comparable to decade-old entry-level parts.

Specification Differences

| Specification | AMD Radeon RX 7900M | Intel Arc B390 |

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

| Manufacturer | AMD | Intel |

| Chip | Navi 31 | Panther Lake |

| Architecture | RDNA 3.0 | Xe3-LPG |

| Process Node | 5 nm | 3 nm |

| Foundry | TSMC | Intel |

| Transistors | 57,700 million | Unknown |

| Die Size | 529 mm² | Unknown |

| Base Clock | 1825 MHz | 300 MHz |

| Boost Clock | 2090 MHz | 2500 MHz |

| Memory Size | 16 GB | System Shared |

| Memory Type | GDDR6 | System Shared |

| Memory Bus | 256 bit | System Shared |

| Memory Bandwidth | 576.0 GB/s | System Dependent |

| Shading Units | 4608 | 1536 |

| TMUs | 288 | 48 |

| ROPs | 192 | 24 |

| Ray Tracing Cores | 72 | 12 |

| Pixel Rate | 401.3 GPixel/s | 60.00 GPixel/s |

| Texture Rate | 601.9 GTexel/s | 120.0 GTexel/s |

| FP32 | 38.52 TFLOPS | 7.680 TFLOPS |

| FP16 | 77.05 TFLOPS (2:1) | 15.36 TFLOPS (2:1) |

| TDP | 180 W | 80 W |

| Bus Interface | PCIe 4.0 x16 | IGP |

| Release Date | 2023-10-18 | 2026-01-26 |