Intel Arc B390 vs NVIDIA GeForce RTX 5060 Comparison

Head-to-Head Benchmarks

The recorded benchmark data contains one direct comparison between the Intel Arc B390 and the NVIDIA GeForce RTX 5060. In the 3DMark Steel Nomad DX12 test, the RTX 5060 scores 3628 points while the Arc B390 scores 1482 points. This represents a delta of -59.2% for the Intel part, meaning the NVIDIA GPU delivers more than double the performance in this specific workload. The RTX 5060 wins the only head-to-head matchup, with a win count of 1 versus 0 for the Arc B390.

The magnitude of the gap is substantial. The RTX 5060's score of 3628 places it at the 72nd percentile among all GPUs in the database, whereas the Arc B390's score of 1482 sits at only the 9th percentile. That percentile spread indicates the two products occupy entirely different performance tiers. The RTX 5060's nearest rivals in the database include the AMD Radeon 860M (26401 average score, -0.3% delta), the NVIDIA GeForce MX550 (26421 average score, -0.3% delta), and the AMD Radeon RX 5700 XT 50th Anniversary (26553 average score, -0.8% delta). The Arc B390's nearest rivals are far lower in the rankings: the NVIDIA GeForce GT 520MX (1463 average score, +1.3% delta), the NVIDIA GeForce 800M (1460 average score, +1.5% delta), and the NVIDIA GeForce GT 625 OEM (1446 average score, +2.5% delta).

Beyond the single head-to-head result, the RTX 5060 has a broader benchmark profile. Its average benchmark score across all recorded tests is 26331, driven by results such as 112787 in Geekbench OpenCL, 113321 in Geekbench Vulkan, and 20891 in Passmark G3D. The Arc B390's average benchmark score is 1482, which matches its Steel Nomad result since that is its only recorded benchmark. The RTX 5060 also shows strong compute performance with a Passmark GPU Compute score of 10899, while the Arc B390 has no comparable compute benchmark in the database.

Architecture Differences

The two GPUs come from fundamentally different design philosophies. The Intel Arc B390 uses the Xe3-LPG architecture built on a 3 nm process at Intel's own foundry. It is based on the Panther Lake chip and belongs to the Arc Graphics-M (Panther Lake) generation. The NVIDIA GeForce RTX 5060 uses the Blackwell 2.0 architecture on a 5 nm process at TSMC, with the GB206 chip and a place in the GeForce 50-series.

The RTX 5060 has a known transistor count of 21,900 million on a die size of 181 mm², giving a transistor density of 121.0M per mm². The Arc B390's transistor count and die size are listed as unknown in the database, so no direct density comparison is possible.

Clock behavior differs notably. The Arc B390 has a base clock of 300 MHz and a boost clock of 2500 MHz, while the RTX 5060 has a base clock of 2280 MHz and a boost clock of 2497 MHz. The Intel part's base clock is dramatically lower, which reflects its integrated design, but its boost clock is nearly identical to the NVIDIA GPU's boost clock. Memory configuration is the most striking divergence. The Arc B390 uses system shared memory, with the memory type, bus width, and bandwidth all dependent on the host system. The RTX 5060 has dedicated 8 GB of GDDR7 memory on a 128-bit bus, delivering 448.0 GB/s of bandwidth.

The compute unit counts are heavily skewed toward the NVIDIA part. The RTX 5060 has 3840 shading units, 120 texture mapping units, 48 raster operations units, 30 ray tracing cores, and 120 tensor cores. The Arc B390 has 1536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores, with no tensor core count listed. Pixel rate for the RTX 5060 is 119.9 GPixel/s versus 60.00 GPixel/s for the Arc B390. Texture rate is 299.6 GTexel/s versus 120.0 GTexel/s. FP32 throughput is 19.18 TFLOPS for the RTX 5060 and 7.680 TFLOPS for the Arc B390. FP16 performance is 19.18 TFLOPS (1:1) for NVIDIA and 15.36 TFLOPS (2:1) for Intel.

Thermal and power specifications also differ. The RTX 5060 has a TDP of 145 W, is a dual-slot card with a 1x 8-pin power connector, and carries a suggested PSU of 300 W. The Arc B390 has an 80 W TDP, is an integrated graphics processor (IGP) with no power connectors, and has no suggested PSU listed. The bus interface for the RTX 5060 is PCIe 5.0 x8, while the Arc B390 uses IGP. Display outputs are 1x HDMI 2.1b and 3x DisplayPort 2.1b for the RTX 5060, while the Arc B390's outputs are listed as portable device dependent.

Where Each One Wins

The RTX 5060 wins in every measurable category from the recorded data. Its 3DMark Steel Nomad score is 2.4 times higher than the Arc B390's score. Its percentile ranking of 72 versus 9 confirms a much stronger position relative to all other GPUs in the database. The RTX 5060 also wins on raw throughput metrics: FP32 compute is 2.5 times higher, texture rate is 2.5 times higher, and pixel rate is 2.0 times higher.

The RTX 5060's memory subsystem gives it a decisive advantage in bandwidth-bound workloads. With 448.0 GB/s of dedicated GDDR7 bandwidth versus system shared memory for the Arc B390, the NVIDIA part avoids the latency and contention issues that can affect integrated graphics solutions. The Arc B390's memory bandwidth is listed as system dependent, meaning its performance will vary based on the host platform's memory configuration.

The Arc B390 has some advantages in specific contexts, though these are not reflected in benchmark scores. Its 80 W TDP is substantially lower than the RTX 5060's 145 W, making it suitable for power-constrained environments. As an integrated GPU with no power connectors and IGP bus interface, it requires no separate card installation and generates less heat. Its 3 nm process node is more advanced than the RTX 5060's 5 nm node, which contributes to its lower power draw. The Arc B390 also supports the same API feature set as the RTX 5060: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

The RTX 5060's tensor cores (120 of them) give it dedicated AI acceleration hardware that the Arc B390 lacks, since no tensor core count is listed for the Intel part. This makes the RTX 5060 better suited for workloads that leverage tensor operations, such as machine learning inference or AI-enhanced rendering features.

FAQ

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

A: The NVIDIA GeForce RTX 5060 scores 3628, while the Intel Arc B390 scores 1482. The RTX 5060 outperforms the Arc B390 by 59.2% in this test.

Q: What is the memory configuration of each GPU?

A: The RTX 5060 has 8 GB of GDDR7 memory on a 128-bit bus with 448.0 GB/s bandwidth. The Arc B390 uses system shared memory, with its type, bus width, and bandwidth dependent on the host system.

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

A: The Arc B390 has a TDP of 80 W and requires no power connectors. The RTX 5060 has a TDP of 145 W and requires a 1x 8-pin power connector, with a suggested PSU of 300 W.

Q: What are the FP32 compute capabilities of each GPU?

A: The RTX 5060 delivers 19.18 TFLOPS of FP32 performance, while the Arc B390 delivers 7.680 TFLOPS. The RTX 5060's FP32 throughput is approximately 2.5 times higher.

Q: Do both GPUs support the same graphics APIs?

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

Q: What is the release timeline for these products?

A: The RTX 5060 was released on May 18, 2025, and the Arc B390 was released on January 26, 2026. Both are listed as Active in production status.

The Verdict

The data indicates a clear performance hierarchy. The NVIDIA GeForce RTX 5060 delivers a 3DMark Steel Nomad score of 3628, placing it at the 72nd percentile of all GPUs, while the Intel Arc B390 achieves 1482, placing it at the 9th percentile. The RTX 5060 wins the only head-to-head benchmark with a 59.2% margin. Its dedicated 8 GB GDDR7 memory, 3840 shading units, and 19.18 TFLOPS FP32 throughput establish it as a discrete graphics card designed for serious gaming and compute workloads.

The Intel Arc B390 is a different class of product. As an integrated GPU with system shared memory, an 80 W TDP, and no power connectors, it targets portable or low-power devices rather than desktop gaming builds. Its 1536 shading units, 12 ray tracing cores, and 7.680 TFLOPS FP32 performance are respectable for an IGP, but they do not approach the RTX 5060's capabilities. The Arc B390's nearest rivals in the database include the NVIDIA GeForce GT 520MX and GeForce 800M, which are entry-level mobile parts.

For users building a desktop system with a dedicated graphics card, the RTX 5060 is the only viable choice based on the recorded data. Its higher percentile ranking, superior compute rates, and larger memory bandwidth all point to substantially better gaming and compute performance. For users requiring a low-power integrated solution, the Arc B390 offers modern API support and a 3 nm process node, but its performance ceiling is far below the RTX 5060. The choice between the two comes down to whether the system can accommodate a discrete card with a 145 W TDP and 1x 8-pin connector, or whether an 80 W IGP with no external power is the requirement.

Specification Differences

| Specification | Intel Arc B390 | NVIDIA GeForce RTX 5060 |

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

| Architecture | Xe3-LPG | Blackwell 2.0 |

| Process Node | 3 nm | 5 nm |

| Foundry | Intel | TSMC |

| Transistors | unknown | 21,900 million |

| Die Size | unknown | 181 mm² |

| Transistor Density | N/A | 121.0M / mm² |

| Base Clock | 300 MHz | 2280 MHz |

| Boost Clock | 2500 MHz | 2497 MHz |

| Memory Size | System Shared | 8 GB |

| Memory Type | System Shared | GDDR7 |

| Memory Bus Width | System Shared | 128 bit |

| Memory Bandwidth | System Dependent | 448.0 GB/s |

| Shading Units | 1536 | 3840 |

| TMUs | 48 | 120 |

| ROPs | 24 | 48 |

| RT Cores | 12 | 30 |

| Tensor Cores | N/A | 120 |

| Pixel Rate | 60.00 GPixel/s | 119.9 GPixel/s |

| Texture Rate | 120.0 GTexel/s | 299.6 GTexel/s |

| FP32 Performance | 7.680 TFLOPS | 19.18 TFLOPS |

| FP16 Performance | 15.36 TFLOPS (2:1) | 19.18 TFLOPS (1:1) |

| TDP | 80 W | 145 W |

| Slot Width | IGP | Dual-slot |

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

| Suggested PSU | N/A | 300 W |

| Bus Interface | IGP | PCIe 5.0 x8 |

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

| Release Date | 2026-01-26 | 2025-05-18 |

| Launch MSRP | N/A | 299 USD |