Intel Arc Pro A60 vs NVIDIA GeForce RTX 5090 Mobile Comparison

Head-to-Head Benchmarks

The database contains two direct benchmark comparisons between the Intel Arc Pro A60 and the NVIDIA GeForce RTX 5090 Mobile, and the results are lopsided. In Geekbench OpenCL, the Intel part scores 63,485 against 201,834 for the NVIDIA part. That is a delta of minus 68.5 percent, meaning the NVIDIA GPU delivers roughly three times the OpenCL performance. The gap is even wider in Geekbench Vulkan, where the Arc Pro A60 posts 57,166 while the RTX 5090 Mobile reaches 198,405, a delta of minus 71.2 percent. NVIDIA wins both head-to-head tests, giving it a clean 2-0 record in this comparison.

These are not subtle margins. A delta of more than 70 percent in Vulkan means the NVIDIA part is not just faster, it is in a different performance tier. The Arc Pro A60's average benchmark score across all recorded tests sits at 60,326, which places it at the 88th percentile of all GPUs in the database. The RTX 5090 Mobile, by contrast, has an average score of 45,152, yet it still sits at the 84th percentile. This apparent contradiction is worth explaining: the NVIDIA part's average is dragged down by several low Passmark scores (DirectX 9 at 324, DirectX 10 at 183, DirectX 11 at 269, DirectX 12 at 138), which are likely recorded under different driver or workload conditions. The two Geekbench results that matter for this head-to-head are unambiguous.

The RTX 5090 Mobile's nearest rivals in the database include the AMD Radeon Pro 5500 XT at 45,384 (0.5 percent below), the NVIDIA GeForce RTX 4070 Ti at 44,795 (0.8 percent above), the Intel Arc A730M at 45,592 (1 percent below), and the NVIDIA RTX 5880 Ada Generation at 45,972 (1.8 percent below). Meanwhile, the Arc Pro A60's nearest rivals are the NVIDIA GeForce RTX 4090 at 60,347 (0 percent delta), the AMD Radeon Pro Vega 48 at 60,140 (0.3 percent above), the AMD Radeon Pro W6600M at 61,896 (2.5 percent above), and the AMD Radeon PRO V710 at 58,657 (2.8 percent below). The Intel card effectively trades blows with an RTX 4090 in average score, which is remarkable for a workstation part, but that comparison does not extend to the RTX 5090 Mobile.

FAQ

Q: Which GPU wins the Geekbench OpenCL test, and by how much?

A: The NVIDIA GeForce RTX 5090 Mobile wins with a score of 201,834 versus 63,485 for the Intel Arc Pro A60. The delta is minus 68.5 percent for the Intel part, meaning NVIDIA is about three times faster.

Q: Is the Intel Arc Pro A60 competitive in Vulkan workloads?

A: No, not against this specific rival. The Arc Pro A60 scores 57,166 in Geekbench Vulkan, while the RTX 5090 Mobile scores 198,405. That is a delta of minus 71.2 percent, the largest gap in this comparison.

Q: What is the average benchmark score for each GPU?

A: The Intel Arc Pro A60 has an average benchmark score of 60,326. The NVIDIA GeForce RTX 5090 Mobile has an average benchmark score of 45,152. The Intel part actually has the higher average, despite losing both head-to-head Geekbench tests.

Q: How do these GPUs rank against all other GPUs in the database?

A: The Intel Arc Pro A60 sits at the 88th percentile, while the NVIDIA GeForce RTX 5090 Mobile sits at the 84th percentile. Both are high-ranking parts, but the Intel card has a slightly higher percentile rank.

Q: Which GPU has more dedicated ray tracing hardware?

A: The NVIDIA GeForce RTX 5090 Mobile has 82 ray tracing cores. The Intel Arc Pro A60 has 16 ray tracing cores. NVIDIA also has 328 tensor cores, while the Intel part lists none.

Q: What memory configurations do these GPUs use?

A: The Intel Arc Pro A60 uses 12 GB of GDDR6 on a 192-bit bus with 384.0 GB/s bandwidth. The NVIDIA GeForce RTX 5090 Mobile uses 24 GB of GDDR7 on a 256-bit bus with 896.0 GB/s bandwidth.

Where Each One Wins

The NVIDIA GeForce RTX 5090 Mobile wins every direct head-to-head benchmark recorded in the database. In OpenCL, it leads by 138,349 points, and in Vulkan it leads by 141,239 points. There is no test in this comparison where the Intel Arc Pro A60 comes out ahead. If a workload uses either OpenCL or Vulkan, the NVIDIA part is the clear choice based on the recorded measurements.

The Intel Arc Pro A60 does have one statistical advantage: its average benchmark score of 60,326 is higher than the NVIDIA part's 45,152. This is because the NVIDIA GPU's average includes several very low Passmark scores (DirectX 9, 10, 11, and 12 all below 325), which pull the mean down substantially. The Intel part has only two recorded benchmarks, both in the 50,000 to 70,000 range, so its average is not diluted by low outlier scores. For a buyer looking at the database summary statistics alone, the Intel card appears stronger on average, but the direct head-to-head data tells the opposite story.

For compute-heavy tasks that use OpenCL or Vulkan, the RTX 5090 Mobile is the winner. For scenarios where the average benchmark score across mixed APIs matters more than peak performance in two specific tests, the Arc Pro A60 holds the higher aggregate number. The practical takeaway is that the NVIDIA part wins where it counts, while the Intel part benefits from a cleaner benchmark record.

Specification Differences

The two GPUs differ on nearly every core specification. The Intel Arc Pro A60 uses the DG2-256 chip with 2,048 shading units, 128 texture mapping units, and 64 ROPs. The NVIDIA GeForce RTX 5090 Mobile uses the GB203 chip with 10,496 shading units, 328 TMUs, and 112 ROPs. NVIDIA has more than five times the shading units and more than double the ROP count.

Clock speeds also differ significantly. The Intel card runs at a 900 MHz base clock and a 2,050 MHz boost clock. The NVIDIA card has a 990 MHz base clock but a lower 1,515 MHz boost clock. Despite the lower boost, the NVIDIA part delivers far higher throughput because of its massive core count. The memory clocks differ too: Intel uses 2,000 MHz with 16 Gbps effective, while NVIDIA uses 1,750 MHz with 28 Gbps effective.

Memory capacity and type are major differentiators. Intel offers 12 GB of GDDR6 on a 192-bit bus, yielding 384.0 GB/s. NVIDIA offers 24 GB of GDDR7 on a 256-bit bus, yielding 896.0 GB/s. That is more than double the bandwidth and double the capacity. The pixel rate is 131.2 GPixel/s for Intel versus 169.7 GPixel/s for NVIDIA. The texture rate is 262.4 GTexel/s for Intel versus 496.9 GTexel/s for NVIDIA. FP32 throughput is 8.397 TFLOPS for Intel versus 31.80 TFLOPS for NVIDIA. FP16 is 16.79 TFLOPS (2:1 ratio) for Intel versus 31.80 TFLOPS (1:1 ratio) for NVIDIA.

Power and physical design also differ. The Intel card has a 130 W TDP, is single-slot, and suggests a 300 W power supply. The NVIDIA part has a 95 W TDP, is listed as an IGP (integrated graphics processor), and has no power connectors or suggested PSU. The Intel card uses PCIe 4.0 x16, while NVIDIA uses PCIe 5.0 x16. Display outputs are 4x DisplayPort 2.0 on Intel, versus "Portable Device Dependent" on NVIDIA. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Architecture Differences

The Intel Arc Pro A60 is built on the Xe-HPG architecture, specifically the Alchemist Pro Series generation. It uses the DG2-256 chip manufactured on a 6 nm process at TSMC, with 11,500 million transistors on a 269 mm² die. The transistor density is 42.8 million per square millimeter. The architecture includes 16 ray tracing cores and no tensor cores.

The NVIDIA GeForce RTX 5090 Mobile is built on the Blackwell 2.0 architecture, part of the GeForce 50-series mobile generation. It uses the GB203 chip manufactured on a 5 nm process at TSMC, with 45,600 million transistors on a 378 mm² die. That is a transistor density of 120.6 million per square millimeter, nearly three times the density of the Intel chip. The architecture includes 82 ray tracing cores and 328 tensor cores.

The process node advantage is clear: 5 nm versus 6 nm, and the NVIDIA chip packs almost four times the transistors into only 40 percent more die area. The tensor core count is a major architectural difference, enabling NVIDIA-specific compute features that the Intel part cannot match since it has no tensor cores at all. The FP16 ratio also differs: Intel runs FP16 at a 2:1 rate relative to FP32, while NVIDIA runs it at 1:1, meaning the NVIDIA part does not halve its throughput when switching to half precision.

The NVIDIA part is a mobile IGP with no power connectors, designed to be integrated into laptops. The Intel part is a single-slot add-in card with a 300 W suggested power supply. The release dates are also far apart: Intel launched on June 5, 2023, while NVIDIA launched on March 26, 2025. The NVIDIA part has a predecessor, the GeForce 40 Mobile series, while the Intel part has no listed predecessor or successor.

The Verdict

The data points to one clear conclusion for anyone choosing between these two GPUs: the NVIDIA GeForce RTX 5090 Mobile is the faster part in every direct benchmark comparison recorded. It wins OpenCL by 68.5 percent and Vulkan by 71.2 percent. Those are not close margins; they represent a performance gap of roughly three times in both APIs. If a workload depends on OpenCL or Vulkan, the NVIDIA part is the only rational choice from this data.

The Intel Arc Pro A60 is not a weak GPU. It sits at the 88th percentile of all GPUs in the database and its average benchmark score of 60,326 puts it within 0 percent of an RTX 4090 in the nearest rivals list. But the RTX 5090 Mobile's raw compute throughput, driven by 10,496 shading units and 328 tensor cores, simply overwhelms the Intel part's 2,048 shading units. The NVIDIA GPU also offers 24 GB of GDDR7 with 896.0 GB/s bandwidth, double the capacity and more than double the bandwidth of the Intel card.

Who should pick the Intel Arc Pro A60? A user who needs a single-slot workstation card with four DisplayPort 2.0 outputs, a 130 W TDP, and a 300 W suggested power supply. The Intel part is also the higher-percentile GPU at 88 versus 84, and its average benchmark score is higher. For professional environments where the card must fit into a constrained chassis and drive multiple displays, the Intel part makes sense.

Who should pick the NVIDIA GeForce RTX 5090 Mobile? Anyone who needs maximum compute performance in OpenCL or Vulkan, more memory, higher bandwidth, or tensor core capabilities. The NVIDIA part has 82 ray tracing cores versus 16, and it runs at a lower 95 W TDP despite delivering far more performance. It is an IGP, so it is not a drop-in card for a desktop, but for a laptop or portable device where performance matters most, the recorded data gives NVIDIA the win in every direct comparison.

The verdict is straightforward: if the choice is between these two specific models, the RTX 5090 Mobile wins on performance, memory, and features. The Arc Pro A60 wins on form factor flexibility and average benchmark score, but the head-to-head results are decisive.