Intel Arc Pro A60 vs NVIDIA GeForce RTX 5070 Mobile Comparison

FAQ

Q: Which GPU shows a higher average benchmark score in the database?

A: The NVIDIA GeForce RTX 5070 Mobile records a higher average benchmark score of 29,928, compared to the Intel Arc Pro A60's average of 60,326. The Intel part's average is inflated by its two recorded OpenCL and Vulkan results, while the NVIDIA part's average includes a broader set of DirectX and compute tests.

Q: How does the Intel Arc Pro A60 compare to its nearest rival, the NVIDIA GeForce RTX 4090?

A: The Arc Pro A60 scores 60,326 on average, which is essentially identical to the RTX 4090's 60,347, showing a delta of 0%. It also sits 2.8% ahead of the AMD Radeon PRO V710 and 0.3% ahead of the AMD Radeon Pro Vega 48.

Q: What is the performance gap between the two GPUs in head-to-head compute tests?

A: In Geekbench OpenCL, the RTX 5070 Mobile scores 122,238 versus the Arc Pro A60's 63,485, a 48.1% advantage for NVIDIA. In Geekbench Vulkan, the RTX 5070 Mobile scores 116,960 versus 57,166, a 51.1% advantage.

Q: Which GPU has more shading units and tensor cores?

A: The RTX 5070 Mobile has 4,608 shading units and 144 tensor cores, while the Arc Pro A60 has 2,048 shading units and no tensor cores listed in the database.

Q: What memory configurations do the two GPUs use?

A: The Arc Pro A60 uses 12 GB of GDDR6 on a 192-bit bus, with 384.0 GB/s of bandwidth. The RTX 5070 Mobile uses 8 GB of GDDR7 on a 128-bit bus, also with 384.0 GB/s of bandwidth despite the narrower bus.

Q: Which GPU has the higher transistor density?

A: The RTX 5070 Mobile has a transistor density of 121.0M per mm², while the Arc Pro A60 has 42.8M per mm². The RTX part packs 21,900 million transistors on a 181 mm² die, versus 11,500 million on a 269 mm² die for the Intel part.

Architecture Differences

The Intel Arc Pro A60 uses the DG2-256 chip built on the Xe-HPG architecture, fabricated by TSMC on a 6 nm process. Its die measures 269 mm² and contains 11,500 million transistors. The NVIDIA GeForce RTX 5070 Mobile uses the GB206 chip with Blackwell 2.0 architecture, also from TSMC but on a 5 nm process. That die is smaller at 181 mm² yet packs 21,900 million transistors, giving it a much higher density.

The compute layouts differ sharply. The Arc Pro A60 has 2,048 shading units, 128 texture mapping units, and 64 ROPs, with 16 ray tracing cores and no tensor core count recorded. The RTX 5070 Mobile has 4,608 shading units, 144 TMUs, and 48 ROPs, with 36 ray tracing cores and 144 tensor cores. The NVIDIA part delivers 13.13 TFLOPS of FP32 and FP16 (1:1), while the Intel part delivers 8.397 TFLOPS of FP32 and 16.79 TFLOPS of FP16 (2:1). Pixel and texture rates also split: the Arc Pro A60 reaches 131.2 GPixel/s and 262.4 GTexel/s, while the RTX 5070 Mobile reaches 68.40 GPixel/s and 205.2 GTexel/s.

Memory architecture diverges as well. The Arc Pro A60 uses 12 GB of GDDR6 over a 192-bit bus, with memory clocked at 2000 MHz (16 Gbps effective) for 384.0 GB/s. The RTX 5070 Mobile uses 8 GB of GDDR7 over a 128-bit bus, with memory at 1500 MHz (24 Gbps effective), also resulting in 384.0 GB/s. Both support PCIe, but the Intel card uses PCIe 4.0 x16 while the NVIDIA mobile part uses PCIe 5.0 x16. Display outputs differ: the Arc Pro A60 has 4x DisplayPort 2.0, whereas the RTX 5070 Mobile's outputs are listed as portable device dependent. The Arc Pro A60 is a single-slot card with a 130 W TDP and a suggested PSU of 300 W, while the RTX 5070 Mobile is an integrated GPU package with a 50 W TDP and no power connectors listed. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

The Verdict

The data points to two very different products. The NVIDIA GeForce RTX 5070 Mobile is the clear compute leader in the recorded head-to-head tests, winning both OpenCL and Vulkan by margins of 48.1% and 51.1% respectively. Its average benchmark score of 29,928, however, sits in the 75th percentile of all GPUs, while the Intel Arc Pro A60 sits in the 88th percentile with an average of 60,326. That apparent contradiction stems from the benchmark sets: the Intel part's two results are both high, while the NVIDIA part's average includes lower DirectX and compute scores.

For raw compute throughput in OpenCL and Vulkan, the RTX 5070 Mobile is the stronger choice. Its FP32 rate of 13.13 TFLOPS exceeds the Arc Pro A60's 8.397 TFLOPS, and it has more than double the shading units. The Arc Pro A60 counters with higher pixel rate, higher texture rate, more ROPs, and double the memory capacity at 12 GB versus 8 GB. The Intel card also draws 130 W versus 50 W for the NVIDIA part, so the mobile GPU delivers its performance at far lower power.

Who should pick which? The RTX 5070 Mobile suits workloads that favor compute-heavy OpenCL and Vulkan execution, especially in power-constrained mobile systems. The Arc Pro A60 suits applications that need higher fill rates, more ROPs, and larger memory capacity in a desktop single-slot form factor. Neither part dominates across all metrics; the choice depends on whether the workload prioritizes shading throughput or rasterization and memory capacity.

Specification Differences

| Specification | Intel Arc Pro A60 | NVIDIA GeForce RTX 5070 Mobile |

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

| Process Node | 6 nm | 5 nm |

| Transistors | 11,500 million | 21,900 million |

| Die Size | 269 mm² | 181 mm² |

| Transistor Density | 42.8M / mm² | 121.0M / mm² |

| Base Clock | 900 MHz | 907 MHz |

| Boost Clock | 2050 MHz | 1425 MHz |

| Memory Clock | 2000 MHz (16 Gbps effective) | 1500 MHz (24 Gbps effective) |

| Memory Size | 12 GB | 8 GB |

| Memory Type | GDDR6 | GDDR7 |

| Memory Bus Width | 192 bit | 128 bit |

| Shading Units | 2048 | 4608 |

| TMUs | 128 | 144 |

| ROPs | 64 | 48 |

| RT Cores | 16 | 36 |

| Tensor Cores | Not listed | 144 |

| Pixel Rate | 131.2 GPixel/s | 68.40 GPixel/s |

| Texture Rate | 262.4 GTexel/s | 205.2 GTexel/s |

| FP32 | 8.397 TFLOPS | 13.13 TFLOPS |

| FP16 | 16.79 TFLOPS (2:1) | 13.13 TFLOPS (1:1) |

| TDP | 130 W | 50 W |

| Slot Width | Single-slot | IGP |

| Power Connectors | Not listed | None |

| Suggested PSU | 300 W | Not listed |

| Bus Interface | PCIe 4.0 x16 | PCIe 5.0 x16 |

| Display Outputs | 4x DisplayPort 2.0 | Portable Device Dependent |

| Release Date | 2023-06-05 | 2025-04-14 |

Head-to-Head Benchmarks

The recorded head-to-head data contains two tests, and NVIDIA wins both decisively. In Geekbench OpenCL, the RTX 5070 Mobile scores 122,238 against the Arc Pro A60's 63,485, a 48.1% difference. In Geekbench Vulkan, the RTX 5070 Mobile scores 116,960 against 57,166, a 51.1% difference. These are the only direct comparisons in the database, and they show a consistent pattern: the NVIDIA part roughly doubles the Intel part's compute scores in both APIs.

The broader benchmark set for the RTX 5070 Mobile adds context. Its PassMark G3D score is 20,355, its GPU compute score is 8,279, and its DirectX scores range from 93 in DirectX 12 to 214 in DirectX 9. The G2D score is 896. These results pull its average down to 29,928, which places it near the NVIDIA GeForce RTX 3070 Ti (29,945, a 0.1% difference) and the AMD Radeon RX 6800 (30,095, a 0.6% difference). The Arc Pro A60, by contrast, has only the two Geekbench results, giving it an average of 60,326 and placing it near the RTX 4090 (60,347, 0% difference) and the AMD Radeon Pro W6600M (61,896, a 2.5% difference).

The percentile rankings confirm the split. The Arc Pro A60 sits in the 88th percentile of all GPUs, while the RTX 5070 Mobile sits in the 75th percentile. That ranking reflects the Intel part's high scores in the limited tests recorded, not a head-to-head superiority. In the two tests where both parts appear, the RTX 5070 Mobile wins by wide margins.

Where Each One Wins

The RTX 5070 Mobile wins in compute-heavy scenarios. Its OpenCL score of 122,238 and Vulkan score of 116,960 both exceed the Arc Pro A60's 63,485 and 57,166 by roughly double. Its FP32 throughput of 13.13 TFLOPS, 4,608 shading units, and 144 tensor cores support this advantage. The 50 W TDP also makes it the lower-power option, which matters for mobile or thermally constrained systems.

The Arc Pro A60 wins in rasterization and memory capacity. It has 64 ROPs versus 48, a pixel rate of 131.2 GPixel/s versus 68.40 GPixel/s, and a texture rate of 262.4 GTexel/s versus 205.2 GTexel/s. It carries 12 GB of memory versus 8 GB, both with identical bandwidth of 384.0 GB/s, but the Intel part achieves that bandwidth over a 192-bit bus with GDDR6 while the NVIDIA part uses a 128-bit bus with GDDR7. The Arc Pro A60 also supports four DisplayPort 2.0 outputs, making it more suitable for multi-display workstation setups, and its PCIe 4.0 x16 interface is adequate for a 130 W single-slot desktop card.

The RTX 5070 Mobile's nearest rivals include the RTX 3070 Ti and RTX 2080 Ti, with deltas of 0.1% and 0.5% respectively, placing it in familiar laptop GPU territory. The Arc Pro A60's nearest rivals include the RTX 4090 and Radeon Pro W6600M, with deltas of 0% and 2.5%, placing it among high-end workstation parts in the database's average score ranking. That positioning, combined with the head-to-head results, indicates the Intel card's strength lies in consistent high scores across its recorded tests rather than in raw compute dominance over the newer NVIDIA part.