AMD Radeon RX 9070 GRE vs Intel Arc B390 Comparison

Head-to-Head Benchmarks

The recorded data contains a single shared benchmark result between these two GPUs: the 3DMark Steel Nomad DX12 test. In that test, the AMD Radeon RX 9070 GRE scores 5424 points, while the Intel Arc B390 scores 1482 points. The AMD card wins by a margin of 266%, meaning it delivers more than three and a half times the performance of the Intel part in this particular workload. This is a decisive victory, and the magnitude of the gap is substantial enough that no other comparative benchmark data is needed to establish a clear hierarchy in raw graphics throughput.

Looking at the broader context from the database, the AMD Radeon RX 9070 GRE ranks in the 87th percentile among all GPUs, with an average benchmark score of 57367 across its recorded tests. Its nearest rivals in the database include the Intel Arc A580 (average score 57756, a delta of -0.7%), the AMD Radeon RX 5600 OEM (average score 58085, a delta of -1.2%), the Intel Arc A570M (average score 58239, a delta of -1.5%), and the AMD Radeon RX 6950 XT (average score 58392, a delta of -1.8%). These deltas are all negative from the perspective of the RX 9070 GRE, meaning it sits slightly below each of those rivals in average score, yet the differences are small (under 2%). This indicates that the RX 9070 GRE occupies a performance tier very close to those established desktop and mobile parts, despite its own Steel Nomad score being lower than its average would suggest.

The Intel Arc B390, by contrast, ranks in the 9th percentile among all GPUs, with an average benchmark score of 1482, which is identical to its single Steel Nomad result. Its nearest rivals are all much older or lower-end NVIDIA parts: the GeForce GT 520MX (average score 1463, a delta of 1.3%), the GeForce 800M (average score 1460, a delta of 1.5%), the GeForce GT 625 OEM (average score 1446, a delta of 2.5%), and the GeForce GT 710 (average score 1443, a delta of 2.7%). Here, the deltas are positive for the Arc B390, meaning it outperforms each of these rivals by a small margin (between 1.3% and 2.7%). This places the Arc B390 at the very bottom of the discrete GPU performance spectrum, roughly on par with entry-level GPUs from over a decade ago.

The head-to-head delta of 266% in Steel Nomad is the only direct comparison available, but it aligns perfectly with the percentile rankings: a 87th-percentile GPU versus a 9th-percentile GPU. The data shows no benchmark where the Intel part wins, and the win count of 1 for AMD versus 0 for Intel confirms this complete dominance in the recorded tests.

Architecture Differences

The two GPUs come from fundamentally different design philosophies and manufacturing processes. The AMD Radeon RX 9070 GRE is built on the RDNA 4.0 architecture, using the Navi 48 chip, and is fabricated on a 4 nm process at TSMC. The integrated circuit contains 53,900 million transistors on a die size of 357 mm², resulting in a transistor density of 151.0 million transistors per square millimeter. This is a large, complex discrete GPU designed for high-end desktop use.

The Intel Arc B390 uses the Xe3-LPG architecture with the Panther Lake chip, fabricated on a 3 nm process at Intel's own foundry. The transistor count and die size are listed as unknown in the database, and no transistor density figure is provided. This reflects its nature as an integrated graphics processor (IGP) rather than a discrete add-in board. The Arc B390 is part of the Arc Graphics-M (Panther Lake) generation, indicating it is designed for mobile or integrated use, not as a standalone card.

Clock speeds differ dramatically. The RX 9070 GRE has a base clock of 1420 MHz, a boost clock of 2790 MHz, and a game clock of 2220 MHz. The Arc B390 has a base clock of 300 MHz and a boost clock of 2500 MHz, with no game clock listed. The AMD part also has dedicated memory clocked at 2250 MHz (18 Gbps effective), while the Intel part uses system shared memory with a clock listed as "System Shared" and bandwidth described as "System Dependent."

Memory configurations are a major differentiator. The RX 9070 GRE has 12 GB of GDDR6 memory on a 192-bit bus, yielding a bandwidth of 432.0 GB/s. The Arc B390 has no dedicated VRAM; its memory size, type, and bus width are all listed as "System Shared," meaning it relies on the host system's main memory. This fundamental difference in memory architecture explains much of the performance gap, as dedicated VRAM provides far higher bandwidth and lower latency than shared system memory.

Compute resources also diverge sharply. The RX 9070 GRE has 3072 shading units, 192 texture mapping units (TMUs), 96 raster operation units (ROPs), and 48 ray tracing cores. The Arc B390 has 1536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores. These are exactly half the shading units, one quarter the TMUs, one quarter the ROPs, and one quarter the ray tracing cores of the AMD part, which directly scales with the observed performance difference.

Pixel rate and texture rate follow the same pattern. The RX 9070 GRE achieves 267.8 GPixel/s and 535.7 GTexel/s, while the Arc B390 achieves 60.00 GPixel/s and 120.0 GTexel/s. FP32 compute is 34.28 TFLOPS for the AMD card versus 7.680 TFLOPS for the Intel part, a ratio of roughly 4.5 to 1. Interestingly, the FP16 figures differ in ratio: the RX 9070 GRE delivers 34.28 TFLOPS FP16 with a 1:1 ratio to FP32, while the Arc B390 delivers 15.36 TFLOPS FP16 with a 2:1 ratio, meaning the Intel part has a relatively stronger FP16 throughput compared to its own FP32 performance.

Power and physical specifications could not be more different. The RX 9070 GRE has a TDP of 220 W, is dual-slot, requires two 8-pin power connectors, and suggests a 550 W power supply. It uses a PCIe 5.0 x16 bus interface. The Arc B390 has a TDP of 80 W, is classified as an IGP with no slot width, requires no power connectors, has no suggested PSU, and uses an IGP bus interface. Display outputs on the AMD card are 1x HDMI 2.1b and 3x DisplayPort 2.1a, while the Intel part's outputs are described as "Portable Device Dependent."

Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The release dates differ: the RX 9070 GRE launched on May 7, 2025, while the Arc B390 is dated January 26, 2026. Both are listed as Active in production status.

Where Each One Wins

The data shows no benchmark wins for the Intel Arc B390. In every recorded metric, the AMD Radeon RX 9070 GRE is ahead. The only head-to-head test, 3DMark Steel Nomad DX12, shows a 266% advantage for AMD.

The RX 9070 GRE wins in every category that matters for gaming and compute workloads. Its 12 GB of dedicated GDDR6 memory with 432.0 GB/s bandwidth provides the memory capacity and throughput needed for modern high-resolution textures and complex scenes. The 3072 shading units and 48 ray tracing cores give it substantial raw compute and ray tracing capability. The 34.28 TFLOPS FP32 performance is suitable for heavy graphics workloads, and the 96 ROPs handle high-resolution rasterization efficiently.

The Arc B390, as an integrated GPU, finds its place in scenarios where its 80 W TDP and lack of power connectors are advantages. It uses system shared memory, which means it does not require a dedicated VRAM allocation, and its IGP bus interface means it is built into a processor rather than installed in a PCIe slot. This makes it suitable for portable devices where space and power are constrained. Its 15.36 TFLOPS FP16 performance with a 2:1 ratio suggests it has proportionally stronger half-precision compute, which could benefit certain AI or compute tasks that use FP16, though the absolute numbers are far below the AMD card.

The percentile rankings tell the story clearly. The RX 9070 GRE sits at the 87th percentile of all GPUs, making it a high-end performer. The Arc B390 sits at the 9th percentile, placing it near the very bottom of the performance distribution. Any user comparing these two parts for gaming or general graphics work would see a massive advantage for the AMD card.

FAQ

Q: How much faster is the AMD Radeon RX 9070 GRE than the Intel Arc B390 in the 3DMark Steel Nomad DX12 test?

A: The RX 9070 GRE scores 5424, while the Arc B390 scores 1482. This gives the AMD card a 266% higher score, meaning it is roughly 3.7 times faster in this benchmark.

Q: What are the memory configurations of these two GPUs?

A: The RX 9070 GRE has 12 GB of GDDR6 memory on a 192-bit bus with 432.0 GB/s bandwidth. The Arc B390 has no dedicated memory; it uses system shared memory with a bus width and bandwidth both listed as "System Shared" and "System Dependent," respectively.

Q: How do these GPUs compare in terms of power consumption?

A: The RX 9070 GRE has a TDP of 220 W, requires two 8-pin power connectors, and suggests a 550 W power supply. The Arc B390 has a TDP of 80 W, requires no power connectors, and has no suggested PSU listed.

Q: What is the transistor count and die size for each chip?

A: The RX 9070 GRE uses a Navi 48 chip with 53,900 million transistors on a 357 mm² die, fabricated on a 4 nm TSMC process. The Arc B390 uses a Panther Lake chip with unknown transistor count and die size, fabricated on a 3 nm Intel process.

Q: Which GPU has more shading units and ray tracing cores?

A: The RX 9070 GRE has 3072 shading units and 48 ray tracing cores. The Arc B390 has 1536 shading units and 12 ray tracing cores, meaning the AMD card has double the shading units and four times the ray tracing cores.

Q: What are the release dates for these products?

A: The AMD Radeon RX 9070 GRE was released on May 7, 2025, while the Intel Arc B390 is dated January 26, 2026. Both are currently listed as Active in production status.

The Verdict

The data is unambiguous. The AMD Radeon RX 9070 GRE is an overwhelmingly faster GPU than the Intel Arc B390. The 266% lead in the sole head-to-head benchmark, combined with the 87th versus 9th percentile rankings, establishes a performance gap that spans multiple tiers of the GPU hierarchy. The RX 9070 GRE's dedicated 12 GB GDDR6 memory, 34.28 TFLOPS FP32 compute, and 48 ray tracing cores place it firmly in the high-end desktop category. The Arc B390, with its shared system memory, 7.680 TFLOPS FP32, and 12 ray tracing cores, is an integrated solution intended for lightweight or mobile use.

A user seeking a GPU for demanding gaming, content creation, or compute work should choose the RX 9070 GRE without hesitation. Its nearest rivals, such as the Intel Arc A580 and AMD Radeon RX 6950 XT, are within 2% of its average score, confirming it belongs to a competitive high-performance tier. The Arc B390's nearest rivals are the GeForce GT 520MX, GeForce 800M, GeForce GT 625 OEM, and GeForce GT 710, all of which are extremely old or low-end parts. This places the Arc B390 in a category suitable only for basic display output or very light workloads.

The choice is not about trade-offs; it is about matching the hardware to the intended use case. The RX 9070 GRE delivers desktop-class performance with a 220 W TDP and dual-slot cooler. The Arc B390 delivers integrated-level performance with an 80 W TDP and no power connectors, making it appropriate for portable devices. The recorded data gives no reason to prefer the Intel part for any graphics-intensive task.

Specification Differences

| Specification | AMD Radeon RX 9070 GRE | Intel Arc B390 |

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

| Architecture | RDNA 4.0 | Xe3-LPG |

| Chip | Navi 48 | Panther Lake |

| Process Node | 4 nm | 3 nm |

| Foundry | TSMC | Intel |

| Transistors | 53,900 million | Unknown |

| Die Size | 357 mm² | Unknown |

| Base Clock | 1420 MHz | 300 MHz |

| Boost Clock | 2790 MHz | 2500 MHz |

| Game Clock | 2220 MHz | None |

| Memory Size | 12 GB | System Shared |

| Memory Type | GDDR6 | System Shared |

| Memory Bus Width | 192 bit | System Shared |

| Memory Bandwidth | 432.0 GB/s | System Dependent |

| Shading Units | 3072 | 1536 |

| TMUs | 192 | 48 |

| ROPs | 96 | 24 |

| Ray Tracing Cores | 48 | 12 |

| Pixel Rate | 267.8 GPixel/s | 60.00 GPixel/s |

| Texture Rate | 535.7 GTexel/s | 120.0 GTexel/s |

| FP32 Performance | 34.28 TFLOPS | 7.680 TFLOPS |

| FP16 Performance | 34.28 TFLOPS (1:1) | 15.36 TFLOPS (2:1) |

| TDP | 220 W | 80 W |

| Slot Width | Dual-slot | IGP |

| Power Connectors | 2x 8-pin | None |

| Suggested PSU | 550 W | None |

| Bus Interface | PCIe 5.0 x16 | IGP |

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

| Release Date | 2025-05-07 | 2026-01-26 |

| Launch MSRP | 549 USD | None |