Intel Arc Pro A60 vs NVIDIA GeForce RTX 5090 D Comparison

Where Each One Wins

The recorded data splits these two cards into completely different performance strata. The NVIDIA GeForce RTX 5090 D wins both shared benchmark tests outright, with no test in the database favoring the Intel Arc Pro A60. That is not a close contest; it is a category separation.

For the RTX 5090 D, the wins are absolute and massive. In Geekbench OpenCL, it scores 310,674 against the Intel's 63,485, a delta of 389.4%. In Geekbench Vulkan, the gap widens further: 376,915 versus 57,166, a 559.3% advantage. These are not incremental margins; they represent a different class of compute throughput. The RTX 5090 D also carries a broader benchmark footprint, with results across 3DMark Steel Nomad DX12, multiple PassMark DirectX tests, PassMark G2D, G3D, and GPU compute. Its average benchmark score sits at 77,712, placing it in the 92nd percentile of all GPUs tracked. The Intel Arc Pro A60, by contrast, has only two recorded benchmarks, both Geekbench entries, and its average score is 60,326, which still lands in the 88th percentile. That percentile figure shows the Intel card is not weak in absolute terms; it is simply outclassed by the NVIDIA part in every shared measurement.

The use-case split is therefore not about which card wins which workload, but about which workloads each card can credibly serve. The RTX 5090 D is a top-tier compute and rendering part. Its PassMark G3D score of 44,065 and GPU compute score of 28,396 indicate strong general 3D and compute performance, while its 3DMark Steel Nomad DX12 result of 14,326 confirms modern DirectX 12 load handling. The Intel Arc Pro A60, with its 8.397 TFLOPS FP32 throughput and 16.79 TFLOPS FP16 (2:1), is a professional workstation-oriented card. Its single-slot design, 130 W TDP, and four DisplayPort 2.0 outputs point to multi-display professional setups rather than raw performance chasing. The database shows the Intel card matching the NVIDIA GeForce RTX 4090 in average score (60,326 versus 60,347, delta 0%), which is a notable alignment for a low-power workstation part. The RTX 5090 D, meanwhile, sits near the AMD Radeon RX 6850M XT (77,712 average against 78,940, delta -1.6%) and the NVIDIA Tesla P100 variants, indicating its average score is influenced by its wider benchmark suite, not by any weakness in the tests it dominates.

Architecture Differences

The two cards come from different architectural generations and design philosophies. The RTX 5090 D uses the GB202 chip, built on NVIDIA's Blackwell 2.0 architecture, fabricated on a 5 nm process at TSMC. The Intel Arc Pro A60 uses the DG2-256 chip, based on Xe-HPG architecture, fabricated on a 6 nm process, also at TSMC. The process node difference is small in name but significant in scale: the RTX 5090 D packs 92,200 million transistors into a 750 mm² die, yielding a transistor density of 122.9 million per mm². The Intel chip contains 11,500 million transistors on a 269 mm² die, for a density of 42.8 million per mm². That is roughly a 2.9x density advantage for the NVIDIA part, and an even larger raw transistor count advantage.

The memory subsystems diverge sharply. The RTX 5090 D has 32 GB of GDDR7 on a 512-bit bus, delivering 1.79 TB/s of bandwidth. The Intel Arc Pro A60 has 12 GB of GDDR6 on a 192-bit bus, delivering 384.0 GB/s. That is a 4.7x bandwidth gap, which directly explains the compute deltas in the benchmarks. The RTX 5090 D also has far more execution resources: 21,760 shading units, 680 TMUs, 176 ROPs, 170 RT cores, and 680 tensor cores. The Intel card has 2,048 shading units, 128 TMUs, 64 ROPs, and 16 RT cores, with no tensor core field recorded in the database. The NVIDIA part's pixel rate is 423.6 GPixel/s and texture rate is 1,636.8 GTexel/s, versus 131.2 GPixel/s and 262.4 GTexel/s for the Intel. The FP32 throughput difference is 104.8 TFLOPS against 8.397 TFLOPS, a 12.5x gap. FP16 is 104.8 TFLOPS (1:1) for NVIDIA versus 16.79 TFLOPS (2:1) for Intel, showing the NVIDIA part does not rely on rate-halving to reach its FP16 numbers.

Clock behavior also differs. The RTX 5090 D has a base clock of 2017 MHz and a boost of 2407 MHz. The Intel card has a base of 900 MHz and a boost of 2050 MHz. The NVIDIA part's higher base clock means it sustains more performance under load, while the Intel card relies on boost to approach competitive frequencies. Power envelopes are on different planets: the RTX 5090 D has a 575 W TDP with a suggested 950 W PSU and a single 16-pin connector, while the Intel card has a 130 W TDP, a suggested 300 W PSU, and no dedicated power connector listed. The RTX 5090 D is dual-slot; the Intel Arc Pro A60 is single-slot. Both support PCIe, but the NVIDIA card uses PCIe 5.0 x16 while the Intel uses PCIe 4.0 x16. Display outputs differ as well: the NVIDIA card has one HDMI 2.1b and three DisplayPort 2.1b, while the Intel card has four DisplayPort 2.0.

Head-to-Head Benchmarks

Only two benchmark tests appear in the shared database for these cards, and the RTX 5090 D wins both. The first is Geekbench OpenCL. The NVIDIA card scores 310,674; the Intel card scores 63,485. The delta is 389.4%, meaning the RTX 5090 D delivers nearly five times the OpenCL performance of the Arc Pro A60. This is the kind of margin that separates high-end compute accelerators from professional workstation cards, and it aligns with the raw FP32 and memory bandwidth differences in the specifications.

The second shared test is Geekbench Vulkan. Here the RTX 5090 D scores 376,915 against the Intel's 57,166, a delta of 559.3%. The Vulkan margin is even larger than OpenCL, which suggests the NVIDIA architecture scales better with the lower-level API. The Intel card's Vulkan score is actually lower than its OpenCL score (57,166 versus 63,485), while the NVIDIA card's Vulkan score is higher than its OpenCL score (376,915 versus 310,674). That inversion indicates the RTX 5090 D benefits from Vulkan's explicit control model, while the Intel part does not gain the same advantage. The absolute scores are informative in context: the RTX 5090 D's Vulkan result is 6.6 times the Intel card's OpenCL result, and its OpenCL result is 5.4 times the Intel card's Vulkan result. No matter which cross-comparison is used, the NVIDIA card maintains a dominant lead.

The database also shows the Intel Arc Pro A60's average score of 60,326 puts it exactly in line with the NVIDIA GeForce RTX 4090, which averages 60,347, a 0% delta. That is a surprising alignment given the RTX 4090's reputation, but the data only reflects the recorded benchmarks for the Intel card, which are limited to the two Geekbench tests. The RTX 5090 D's nearest rivals in average score are the AMD Radeon RX 6850M XT (78,940, delta -1.6%), the NVIDIA Tesla P100 PCIe 16 GB (79,605, delta -2.4%), and the Tesla P100 PCIe 12 GB (79,396, delta -2.1%). The RTX 5090 D trails those parts in average score because its benchmark suite includes demanding tests like 3DMark Steel Nomad and multiple PassMark DirectX entries, which pull the average down relative to its Geekbench dominance. The Intel card's nearest rivals include the AMD Radeon Pro W6600M (61,896, delta -2.5%) and the AMD Radeon PRO V710 (58,657, delta 2.8%), showing it sits in a professional midrange cluster.

FAQ

Q: Which card has higher raw compute performance?

A: The NVIDIA GeForce RTX 5090 D. Its FP32 throughput is 104.8 TFLOPS versus 8.397 TFLOPS for the Intel Arc Pro A60, and its FP16 is 104.8 TFLOPS (1:1) against 16.79 TFLOPS (2:1). In Geekbench OpenCL and Vulkan, the NVIDIA card leads by 389.4% and 559.3%, respectively.

Q: How do the memory subsystems compare?

A: The RTX 5090 D has 32 GB of GDDR7 on a 512-bit bus with 1.79 TB/s bandwidth. The Intel Arc Pro A60 has 12 GB of GDDR6 on a 192-bit bus with 384.0 GB/s bandwidth. The NVIDIA card's bandwidth is 4.7 times higher.

Q: What is the power consumption difference?

A: The RTX 5090 D has a 575 W TDP with a suggested 950 W PSU. The Intel Arc Pro A60 has a 130 W TDP with a suggested 300 W PSU. The Intel card is also single-slot, while the NVIDIA card is dual-slot.

Q: Which card is better for professional multi-display setups?

A: The Intel Arc Pro A60 offers four DisplayPort 2.0 outputs and a single-slot design, which suits dense workstation configurations. The RTX 5090 D has one HDMI 2.1b and three DisplayPort 2.1b outputs.

Q: How does the Intel card compare to the RTX 5090 D in average benchmark score?

A: The RTX 5090 D averages 77,712 across its full benchmark suite, placing in the 92nd percentile. The Intel Arc Pro A60 averages 60,326, placing in the 88th percentile. The NVIDIA card's average is 28.8% higher, though the Intel card's percentile is still strong.

Q: Are there any tests where the Intel card wins?

A: No. In the recorded head-to-head benchmarks, the RTX 5090 D wins both Geekbench OpenCL and Geekbench Vulkan. The database shows zero wins for the Intel Arc Pro A60 in shared tests.

Specification Differences

| Specification | NVIDIA GeForce RTX 5090 D | Intel Arc Pro A60 |

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

| Architecture | Blackwell 2.0 | Xe-HPG |

| Process node | 5 nm | 6 nm |

| Transistors | 92,200 million | 11,500 million |

| Die size | 750 mm² | 269 mm² |

| Transistor density | 122.9M / mm² | 42.8M / mm² |

| Base clock | 2017 MHz | 900 MHz |

| Boost clock | 2407 MHz | 2050 MHz |

| Memory size | 32 GB | 12 GB |

| Memory type | GDDR7 | GDDR6 |

| Memory bus width | 512 bit | 192 bit |

| Memory bandwidth | 1.79 TB/s | 384.0 GB/s |

| Shading units | 21,760 | 2,048 |

| TMUs | 680 | 128 |

| ROPs | 176 | 64 |

| RT cores | 170 | 16 |

| Tensor cores | 680 | Not recorded |

| Pixel rate | 423.6 GPixel/s | 131.2 GPixel/s |

| Texture rate | 1,636.8 GTexel/s | 262.4 GTexel/s |

| FP32 performance | 104.8 TFLOPS | 8.397 TFLOPS |

| FP16 performance | 104.8 TFLOPS (1:1) | 16.79 TFLOPS (2:1) |

| TDP | 575 W | 130 W |

| Slot width | Dual-slot | Single-slot |

| Power connectors | 1x 16-pin | Not recorded |

| Suggested PSU | 950 W | 300 W |

| Bus interface | PCIe 5.0 x16 | PCIe 4.0 x16 |

| Display outputs | 1x HDMI 2.1b, 3x DisplayPort 2.1b | 4x DisplayPort 2.0 |

| Release date | 2025-01-29 | 2023-06-05 |

| Launch MSRP | 2,299 USD | Not recorded |