Intel Arc Pro A60 vs NVIDIA N1X 40SM Comparison

Head-to-Head Benchmarks

The recorded data for the Intel Arc Pro A60 shows a pair of OpenCL and Vulkan results, while the NVIDIA N1X 40SM currently has no benchmark entries in the database. This asymmetry makes a direct score-to-score comparison impossible. Instead, the analysis must rely on the Intel part’s measured performance and the architectural specifications of both chips.

The Intel Arc Pro A60 delivers a Geekbench OpenCL score of 63,485 and a Geekbench Vulkan score of 57,166. Its average benchmark score across these two tests is 60,326. This places the card at the 88th percentile among all GPUs in the database. The Vulkan result trails the OpenCL result by roughly 11 percent, which is a common pattern for workstation-oriented drivers where compute workloads often scale more aggressively than graphics workloads under the Vulkan API.

The nearest rivals for the Arc Pro A60, based on average benchmark scores, include the NVIDIA GeForce RTX 4090 at 60,347, which is effectively identical with a delta of 0 percent. The AMD Radeon Pro Vega 48 scores 60,140, putting it 0.3 percent behind the Intel card. The AMD Radeon Pro W6600M leads the Arc Pro A60 by 2.5 percent with a score of 61,896, while the AMD Radeon PRO V710 trails by 2.8 percent at 58,657.

These margins are remarkably tight. The Arc Pro A60 sits within a 2.8 percent band of four different competitors, spanning both consumer flagship and professional-class hardware. The delta of 0 percent against the RTX 4090 is particularly striking, as it indicates that in the database’s average benchmark metric, the Intel workstation card matches a top-tier consumer GPU. The Radeon Pro W6600M is the only rival in this group that edges ahead, and it does so by a slim margin.

For the NVIDIA N1X 40SM, the absence of benchmark scores means no wins can be recorded. The head-to-head benchmark table is empty, and the wins counters for both products are zero. The N1X 40SM’s percentile ranking of 50 reflects its position relative to all GPUs based on available data, but with an average benchmark score of zero, this percentile is provisional until actual measurements are entered.

The performance picture for the N1X 40SM must therefore be inferred from its compute specifications rather than measured results. The chip lists 5,120 shading units, 320 texture mapping units, and 40 render output units. Its FP32 throughput is rated at 24.02 TFLOPS, which is roughly 2.9 times the Arc Pro A60’s 8.397 TFLOPS. The texture rate of 750.7 GTexel/s is about 2.9 times higher than the Intel part’s 262.4 GTexel/s. These figures suggest a substantially higher raw compute ceiling, but the lack of benchmark data prevents confirmation of real-world scaling.

The Arc Pro A60’s pixel rate of 131.2 GPixel/s exceeds the N1X 40SM’s 93.84 GPixel/s by about 40 percent. This is a direct consequence of the Intel card’s 64 ROPs versus the NVIDIA part’s 40 ROPs, combined with the Arc Pro A60’s 2050 MHz boost clock. For fill-rate-bound workloads such as heavy rasterization or certain image processing tasks, the Intel card holds a clear specification advantage.

Memory configurations diverge sharply. The Arc Pro A60 uses 12 GB of GDDR6 across a 192-bit bus, delivering 384.0 GB/s of bandwidth. The N1X 40SM uses 128 GB of LPDDR5X across a 256-bit bus, but its bandwidth is lower at 273.2 GB/s. The NVIDIA part offers more than ten times the capacity, but the Intel card provides roughly 40 percent more bandwidth. This split favors the Arc Pro A60 for bandwidth-sensitive tasks and the N1X 40SM for capacity-driven workloads such as large model inference or massive dataset manipulation.

The Verdict

The data indicates two very different products with distinct strengths. The Intel Arc Pro A60 is the only one of the two with measured benchmark results, and those results place it in the upper tier of all GPUs at the 88th percentile. Its average score of 60,326 puts it in direct competition with the NVIDIA GeForce RTX 4090, AMD Radeon Pro Vega 48, AMD Radeon Pro W6600M, and AMD Radeon PRO V710, with deltas ranging from -2.5 percent to +2.8 percent. For any workload that depends on OpenCL or Vulkan performance, the Arc Pro A60 is a proven quantity.

The NVIDIA N1X 40SM cannot be evaluated on measured performance because no benchmark entries exist. Its specification sheet, however, indicates a much higher compute density: 24.02 TFLOPS FP32, 750.7 GTexel/s texture throughput, and 160 tensor cores. The Blackwell 2.0 architecture and PCIe 5.0 x16 interface position it as a newer, higher-bandwidth-interface design. The 128 GB memory capacity is unprecedented in the database for a GPU of this class, and the 5 nm TSMC process node is one step ahead of the Arc Pro A60’s 6 nm node.

The verdict from the recorded data is straightforward: the Arc Pro A60 is the validated performer, while the N1X 40SM is an unproven specification. For users who require immediate, benchmark-confirmed results, the Arc Pro A60 is the only defensible choice. For users who prioritize raw compute capacity, memory size, and architectural novelty, the N1X 40SM offers a compelling spec sheet that awaits verification.

Where Each One Wins

The Arc Pro A60 wins in every measured category because it is the only product with benchmark scores. Its OpenCL result of 63,485 and Vulkan result of 57,166 establish real-world baselines. The card also wins on memory bandwidth at 384.0 GB/s versus 273.2 GB/s, pixel fill rate at 131.2 GPixel/s versus 93.84 GPixel/s, and ROP count at 64 versus 40. Its boost clock of 2050 MHz is lower than the N1X 40SM’s 2346 MHz, but the Intel card’s higher ROP count compensates in fill-rate terms.

The Arc Pro A60 also supports a full modern API stack: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The N1X 40SM lists N/A for DirectX, OpenGL, and Vulkan, which means its API compatibility is undocumented in the database. The Intel card provides four DisplayPort 2.0 outputs, while the NVIDIA part provides a single HDMI output. For multi-display workstation setups, the Arc Pro A60 is clearly better equipped.

The N1X 40SM wins on raw compute specifications. Its FP32 throughput of 24.02 TFLOPS is 2.9 times higher than the Arc Pro A60’s 8.397 TFLOPS. Its FP16 throughput is also 24.02 TFLOPS with a 1:1 ratio, whereas the Arc Pro A60 achieves 16.79 TFLOPS with a 2:1 ratio. The N1X 40SM’s 160 tensor cores provide dedicated AI acceleration hardware, which the Arc Pro A60 lacks entirely. The texture rate of 750.7 GTexel/s is 2.9 times higher, and the shading unit count of 5,120 is 2.5 times higher. The memory capacity of 128 GB is 10.7 times larger than 12 GB, and the PCIe 5.0 x16 interface doubles the bandwidth of the Arc Pro A60’s PCIe 4.0 x16 link.

The N1X 40SM also wins on process node, using TSMC’s 5 nm process versus the Arc Pro A60’s 6 nm. The NVIDIA chip has a larger die at 382 mm² versus 269 mm², and its boost clock of 2346 MHz exceeds the Intel card’s 2050 MHz. The 40 RT cores on the NVIDIA part outnumber the 16 RT cores on the Intel part by 2.5 times.

For compute-heavy workloads such as FP32 simulation, FP16 machine learning training, or tensor-core-accelerated inference, the N1X 40SM’s specifications indicate a substantial advantage. For memory-bandwidth-bound tasks, rasterization-heavy graphics, or OpenCL/Vulkan compute, the Arc Pro A60’s measured results and higher bandwidth give it the edge.

FAQ

Q: Which GPU has a higher average benchmark score?

A: Only the Intel Arc Pro A60 has recorded benchmarks. Its average score is 60,326. The NVIDIA N1X 40SM has no benchmark entries, so its average score is zero.

Q: How does the Arc Pro A60 compare to its nearest rivals?

A: The Arc Pro A60’s average score of 60,326 is 0 percent different from the NVIDIA GeForce RTX 4090 at 60,347, 0.3 percent ahead of the AMD Radeon Pro Vega 48 at 60,140, 2.5 percent behind the AMD Radeon Pro W6600M at 61,896, and 2.8 percent ahead of the AMD Radeon PRO V710 at 58,657.

Q: What is the memory capacity difference between the two GPUs?

A: The NVIDIA N1X 40SM has 128 GB of LPDDR5X memory, while the Intel Arc Pro A60 has 12 GB of GDDR6. The NVIDIA part offers 10.7 times more capacity.

Q: Which GPU has higher memory bandwidth?

A: The Intel Arc Pro A60 has 384.0 GB/s of bandwidth, compared to 273.2 GB/s for the NVIDIA N1X 40SM. The Intel card provides roughly 40 percent more bandwidth.

Q: Does the NVIDIA N1X 40SM support DirectX, OpenGL, or Vulkan?

A: The database lists N/A for DirectX, OpenGL, and Vulkan support on the NVIDIA N1X 40SM. The Intel Arc Pro A60 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What are the FP32 compute ratings for each GPU?

A: The NVIDIA N1X 40SM is rated at 24.02 TFLOPS FP32, while the Intel Arc Pro A60 is rated at 8.397 TFLOPS. The NVIDIA part is approximately 2.9 times higher.

Architecture Differences

The Intel Arc Pro A60 uses the DG2-256 chip built on TSMC’s 6 nm process node. The architecture is Xe-HPG, part of the Alchemist generation in Intel’s Pro Series. The die measures 269 mm² and contains 11,500 million transistors, yielding a transistor density of 42.8 million per mm². The card is a single-slot design with a 130 W TDP and a suggested power supply of 300 W. It connects via PCIe 4.0 x16 and provides four DisplayPort 2.0 outputs.

The NVIDIA N1X 40SM uses the GB20B chip built on TSMC’s 5 nm process node. The architecture is Blackwell 2.0, part of the Blackwell IGP generation under the N1x family. The die measures 382 mm², which is 42 percent larger than the Intel chip. Transistor count is listed as unknown, and transistor density is not recorded. The N1X 40SM is an integrated graphics processor (IGP) with no power connectors and no TDP listed. It connects via PCIe 5.0 x16 and provides a single HDMI output.

Compute resources differ significantly. The N1X 40SM has 5,120 shading units, 320 TMUs, 40 ROPs, 40 RT cores, and 160 tensor cores. The Arc Pro A60 has 2,048 shading units, 128 TMUs, 64 ROPs, and 16 RT cores, with no tensor cores. The NVIDIA part has 2.5 times more shading units, 2.5 times more TMUs, 2.5 times more RT cores, and 2.5 times more ROPs. The Intel part has 1.6 times more ROPs, which partially offsets the raw compute deficit in pixel throughput.

Clock behavior also differs. The Arc Pro A60 runs at a 900 MHz base clock and boosts to 2050 MHz. The N1X 40SM runs at a 741 MHz base clock and boosts to 2346 MHz. The NVIDIA part has a 14 percent higher boost clock, but the Intel part’s base clock is 21 percent higher.

Memory architecture diverges completely. The Arc Pro A60 uses 12 GB of GDDR6 with a 192-bit bus and 2000 MHz memory clock, translating to 16 Gbps effective and 384.0 GB/s bandwidth. The N1X 40SM uses 128 GB of LPDDR5X with a 256-bit bus and 1067 MHz memory clock, translating to 8.5 Gbps effective and 273.2 GB/s bandwidth. The NVIDIA part sacrifices bandwidth for capacity, while the Intel part does the reverse.

API support is another differentiator. The Arc Pro A60 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The N1X 40SM lists N/A for all three APIs, suggesting that its software stack is either undocumented or not yet validated in the database. The Arc Pro A60’s display outputs consist of four DisplayPort 2.0 connections, whereas the N1X 40SM provides a single HDMI port.

The release timeline places the Arc Pro A60 in June 2023, while the N1X 40SM is dated May 2026 in the database. Both products are marked as active in production. The Arc Pro A60 has a percentile ranking of 88 among all GPUs, while the N1X 40SM sits at the 50th percentile, reflecting its lack of measured data rather than any performance assessment.

The architectural comparison shows two approaches: the Arc Pro A60 is a mature, validated workstation GPU with balanced rasterization and compute capabilities, while the N1X 40SM is a newer, specification-heavy design with massive compute, memory, and AI acceleration resources that have not yet been verified through benchmarks.