Intel Arc Pro A60 vs NVIDIA GeForce RTX 4090 Mobile Comparison

Head-to-Head Benchmarks

The recorded data shows a decisive performance gap between these two GPUs, with the NVIDIA GeForce RTX 4090 Mobile winning both head-to-head benchmark comparisons. The Intel Arc Pro A60 does not secure a single win in the available test set, while the NVIDIA part dominates across the board.

In the Geekbench OpenCL test, the NVIDIA GeForce RTX 4090 Mobile scores 180,831, while the Intel Arc Pro A60 manages 63,485. That is a delta of -64.9% for the Intel card, meaning the NVIDIA part is approximately 185% faster in raw compute workloads as measured by OpenCL. The margin is substantial enough that the Intel GPU falls into a completely different performance tier.

The Vulkan results tell a similar story. The RTX 4090 Mobile posts 170,774 points, while the Arc Pro A60 trails with 57,166, a delta of -66.5%. This is the largest relative gap in the head-to-head dataset, indicating that the NVIDIA architecture holds an even greater advantage in Vulkan-based rendering workloads than it does in OpenCL.

To contextualize these numbers, the Intel Arc Pro A60's average benchmark score of 60,326 places it at the 88th percentile of all GPUs in the database. Its nearest rival is the NVIDIA GeForce RTX 4090 (desktop) with an average score of 60,347, a delta of 0%. The AMD Radeon Pro W6600M sits slightly ahead at 61,896 (+2.5% relative to the Arc), while the AMD Radeon Pro Vega 48 is nearly tied at 60,140 (+0.3% for the Arc). The AMD Radeon PRO V710 trails at 58,657 (2.8% behind the Arc).

The NVIDIA GeForce RTX 4090 Mobile, by contrast, has an average benchmark score of 43,667, which places it at the 84th percentile. Its nearest rivals include the NVIDIA RTX A6000 at 44,075 (-0.9% relative to the mobile card), the NVIDIA Quadro M6000 at 43,301 (+0.8%), and the NVIDIA GeForce RTX 5050 Mobile at 43,268 (+0.9%). This clustering suggests the RTX 4090 Mobile sits comfortably in a professional-grade performance bracket, despite its mobile form factor.

The discrepancy between the average scores and the head-to-head results is noteworthy. The Arc Pro A60 has a higher average benchmark score than the RTX 4090 Mobile, yet loses decisively in the two shared tests. This indicates that the head-to-head tests (OpenCL and Vulkan) favor the NVIDIA architecture much more strongly than other benchmarks in the database, possibly due to driver optimization or architectural differences in compute dispatch.

Architecture Differences

The underlying silicon tells a tale of two very different design philosophies. The Intel Arc Pro A60 uses the DG2-256 chip, built on TSMC's 6 nm process, with 11,500 million transistors packed into a 269 mm² die. That works out to a transistor density of 42.8 million per square millimeter. The NVIDIA GeForce RTX 4090 Mobile, in contrast, uses the AD103 chip on TSMC's 5 nm node, with 45,900 million transistors across a 379 mm² die, yielding 121.1 million transistors per square millimeter.

The density gap is stark: NVIDIA packs nearly three times as many transistors per unit area. This reflects the more advanced 5 nm process and the sheer scale of the AD103 design. The Intel chip is smaller in absolute terms, but the NVIDIA part has 4x the transistor count.

In terms of compute resources, the RTX 4090 Mobile deploys 9,728 shading units, 304 TMUs, and 112 ROPs. The Arc Pro A60 counters with 2,048 shading units, 128 TMUs, and 64 ROPs. The NVIDIA GPU has roughly 4.75x the shading units, 2.4x the TMUs, and 1.75x the ROPs. Ray tracing hardware is similarly lopsided: 76 RT cores on the NVIDIA chip versus 16 on the Intel part.

The NVIDIA GPU also includes 304 tensor cores, a feature category where the Intel Arc Pro A60 has no listed equivalent. This gives the RTX 4090 Mobile a hardware advantage for AI-accelerated workloads, though the database records no specific tensor-core benchmark results for either card.

Clock speeds differ in an interesting way. The Intel card has a lower base clock (900 MHz versus 1,335 MHz) but a higher boost clock (2,050 MHz versus 1,695 MHz). This suggests the Intel GPU is designed to ramp more aggressively under load, while the NVIDIA part maintains a more consistent clock envelope. Memory clocks also favor NVIDIA: 2,250 MHz (18 Gbps effective) versus 2,000 MHz (16 Gbps effective).

Both GPUs share the same API support: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both use PCIe 4.0 x16 interfaces. However, the memory subsystems diverge significantly. The Intel card has 12 GB of GDDR6 on a 192-bit bus, yielding 384.0 GB/s of bandwidth. The NVIDIA card has 16 GB of GDDR6 on a 256-bit bus, delivering 576.0 GB/s. The NVIDIA part enjoys 50% more memory bandwidth, which is critical for high-resolution textures and compute-heavy workloads.

The TDP figures are surprisingly close given the performance gap: 130 W for the Intel card versus 120 W for the NVIDIA mobile part. However, these figures must be interpreted with caution. The Intel card is a single-slot add-in card, while the NVIDIA part is an integrated GPU (IGP) for laptops, with no power connectors and display outputs described as "portable device dependent." The Intel card offers 4x DisplayPort 2.0 outputs, suggesting a workstation-oriented design with multi-monitor support.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The Intel Arc Pro A60 has an average benchmark score of 60,326, while the NVIDIA GeForce RTX 4090 Mobile scores 43,667. However, this difference is misleading, as the head-to-head tests show the NVIDIA part winning decisively.

Q: What is the largest performance gap between the two in a shared benchmark?

A: The largest gap is in Geekbench Vulkan, where the NVIDIA GeForce RTX 4090 Mobile scores 170,774 versus 57,166 for the Intel Arc Pro A60, a delta of -66.5% for the Intel card.

Q: Does the Intel Arc Pro A60 have any benchmark wins over the RTX 4090 Mobile?

A: No. In the recorded head-to-head data, the Intel card wins 0 tests, while the NVIDIA part wins 2 tests.

Q: How do the two GPUs compare in memory bandwidth?

A: The NVIDIA GeForce RTX 4090 Mobile has 576.0 GB/s of bandwidth from 16 GB of GDDR6 on a 256-bit bus. The Intel Arc Pro A60 has 384.0 GB/s from 12 GB of GDDR6 on a 192-bit bus.

Q: Which GPU has more shading units?

A: The NVIDIA GeForce RTX 4090 Mobile has 9,728 shading units, compared to 2,048 on the Intel Arc Pro A60, a ratio of roughly 4.75 to 1.

Q: What is the process node difference between the two chips?

A: The Intel Arc Pro A60 is built on TSMC's 6 nm process, while the NVIDIA GeForce RTX 4090 Mobile uses TSMC's 5 nm process. The NVIDIA chip achieves a transistor density of 121.1M per mm² versus 42.8M per mm² for Intel.

The Verdict

The data points to a clear conclusion: the NVIDIA GeForce RTX 4090 Mobile is in a different performance class than the Intel Arc Pro A60, at least in the two shared benchmarks. The delta of -64.9% in OpenCL and -66.5% in Vulkan leaves no room for ambiguity. For anyone prioritizing raw compute or graphics throughput in these workloads, the NVIDIA part is the obvious choice.

However, the Intel Arc Pro A60 has its own strengths that the data supports. Its average benchmark score of 60,326 is higher than the RTX 4090 Mobile's 43,667, and it sits at the 88th percentile of all GPUs versus the 84th percentile for the NVIDIA card. This suggests that in other, unshared benchmark categories, the Intel card performs competitively against professional workstation GPUs. Its nearest rival is the NVIDIA GeForce RTX 4090 (desktop) with a 0% delta, indicating that the Arc Pro A60 holds its own in certain workloads.

The RTX 4090 Mobile's nearest rivals are professional cards like the NVIDIA RTX A6000 and Quadro M6000, with deltas of -0.9% and +0.8% respectively. This places the mobile NVIDIA part in the same league as high-end workstation accelerators, despite its laptop-oriented design.

For professional workstation use, the Intel Arc Pro A60 offers a single-slot form factor, 4x DisplayPort 2.0 outputs, and a 300 W suggested PSU, making it a straightforward drop-in for multi-monitor setups. The NVIDIA part, being an IGP, is constrained to portable devices and cannot be installed in a desktop system. For laptop users, the RTX 4090 Mobile is the only option of the two.

The TDP figures are nearly identical (130 W versus 120 W), meaning the NVIDIA part delivers vastly more performance per watt in the shared benchmarks. This efficiency advantage is a direct result of the denser 5 nm process and larger transistor budget.

Specification Differences

| Specification | Intel Arc Pro A60 | NVIDIA GeForce RTX 4090 Mobile |

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

| Chip | DG2-256 | AD103 |

| Architecture | Xe-HPG (Alchemist) | Ada Lovelace |

| Process Node | 6 nm | 5 nm |

| Transistors | 11,500 million | 45,900 million |

| Die Size | 269 mm² | 379 mm² |

| Transistor Density | 42.8M / mm² | 121.1M / mm² |

| Base Clock | 900 MHz | 1,335 MHz |

| Boost Clock | 2,050 MHz | 1,695 MHz |

| Memory Clock | 2,000 MHz (16 Gbps) | 2,250 MHz (18 Gbps) |

| Memory Size | 12 GB | 16 GB |

| Memory Bus Width | 192 bit | 256 bit |

| Memory Bandwidth | 384.0 GB/s | 576.0 GB/s |

| Shading Units | 2,048 | 9,728 |

| TMUs | 128 | 304 |

| ROPs | 64 | 112 |

| RT Cores | 16 | 76 |

| Tensor Cores | None listed | 304 |

| Pixel Rate | 131.2 GPixel/s | 189.8 GPixel/s |

| Texture Rate | 262.4 GTexel/s | 515.3 GTexel/s |

| FP32 Performance | 8.397 TFLOPS | 32.98 TFLOPS |

| FP16 Performance | 16.79 TFLOPS (2:1) | 32.98 TFLOPS (1:1) |

| TDP | 130 W | 120 W |

| Slot Width | Single-slot | IGP |

| Power Connectors | None listed | None |

| Suggested PSU | 300 W | Not listed |

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

| Release Date | 2023-06-05 | 2023-01-02 |

| Production Status | Active | Active |

Where Each One Wins

The NVIDIA GeForce RTX 4090 Mobile wins decisively in the two shared benchmark categories: Geekbench OpenCL and Geekbench Vulkan. The margins are substantial, with the NVIDIA part scoring 2.8x higher in OpenCL and 3.0x higher in Vulkan. This indicates that for general-purpose compute (OpenCL) and cross-platform graphics (Vulkan), the RTX 4090 Mobile is categorically superior.

The Intel Arc Pro A60 wins in the broader average benchmark score comparison, posting 60,326 versus 43,667 for the NVIDIA part. This suggests that in benchmark categories not shared between the two (such as the PassMark suite, which the NVIDIA card has results for but the Intel card does not), the Intel GPU demonstrates competitive performance. The Arc Pro A60 also wins on the percentile measure, sitting at the 88th percentile versus the 84th for the NVIDIA part.

For workstation-specific use cases, the Intel card's 4x DisplayPort 2.0 outputs and single-slot design make it suitable for multi-monitor professional setups. The NVIDIA part's "portable device dependent" display outputs mean it relies entirely on the laptop's own display implementation.

For efficiency, the NVIDIA card delivers roughly 3x the FP32 throughput (32.98 TFLOPS versus 8.397 TFLOPS) at a lower TDP (120 W versus 130 W). This makes the RTX 4090 Mobile the clear winner for performance-per-watt, a critical factor in mobile devices where thermal and power budgets are tight.

For memory-intensive workloads, the NVIDIA card's 576.0 GB/s bandwidth versus 384.0 GB/s gives it a 50% advantage, which can be decisive for large datasets or high-resolution textures. The RTX 4090 Mobile also wins on memory capacity at 16 GB versus 12 GB.

The Intel Arc Pro A60 wins on boost clock speed (2,050 MHz versus 1,695 MHz), though this does not translate into a performance advantage in the recorded benchmarks. The Intel card also has a lower base clock (900 MHz versus 1,335 MHz), suggesting a more aggressive dynamic clocking strategy.

For AI or tensor-based workloads, the NVIDIA card's 304 tensor cores give it a hardware feature that the Intel card does not list, though no direct benchmark data is available in this comparison.