Intel Arc Pro A60 vs NVIDIA H20 NVL16 Comparison

Head-to-Head Benchmarks

The Intel Arc Pro A60 and NVIDIA H20 NVL16 occupy entirely different segments of the GPU market, and their benchmark records reflect that divide. The Intel part has two recorded benchmark results in the database, while the NVIDIA H20 NVL16 has no benchmark entries at all, giving it an average benchmark score of zero. This absence of data is itself a meaningful finding: the H20 NVL16 is a server accelerator that ships without display outputs and focuses on compute workloads that are not captured by the standard consumer benchmark suites used in this database.

The Arc Pro A60 records a Geekbench OpenCL score of 63,485 and a Geekbench Vulkan score of 57,166, producing an average benchmark score of 60,326. That average places it at the 88th percentile of all GPUs tracked in the database. Its nearest rival in the rankings is the NVIDIA GeForce RTX 4090, which posts an average score of 60,347, a delta of 0 percent, meaning the two are effectively tied in aggregate performance. The AMD Radeon Pro Vega 48 sits 0.3 percent ahead, and the AMD Radeon Pro W6600M leads by 2.5 percent. The AMD Radeon PRO V710 trails by 2.8 percent. These deltas are remarkably tight, with the entire cluster of five GPUs spanning less than 6 percentage points. The data indicates the Arc Pro A60 lands in the middle of a dense performance band rather than at the top or bottom of it.

The H20 NVL16, by contrast, shows a 50th percentile ranking and no rival comparisons available in the database. With no recorded scores, any direct numeric comparison between these two cards is impossible from the available data. What the database does show are two GPUs with vastly different design goals: one is a workstation-oriented card with a 130 W power target and a single-slot footprint, the other is a 400 W SXM module built for server integration.

FAQ

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

A: The Intel Arc Pro A60 has an average benchmark score of 60,326, while the NVIDIA H20 NVL16 has no recorded benchmarks, leaving its average score at zero.

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

A: The Arc Pro A60 is tied with the NVIDIA GeForce RTX 4090 at a 0 percent delta, sits 0.3 percent behind the AMD Radeon Pro Vega 48, trails the AMD Radeon Pro W6600M by 2.5 percent, and leads the AMD Radeon PRO V710 by 2.8 percent.

Q: What memory configurations do the two cards use?

A: The Arc Pro A60 uses 12 GB of GDDR6 memory on a 192-bit bus with 384.0 GB/s of bandwidth. The H20 NVL16 uses 96 GB of HBM3 memory on a 6144-bit bus with 4.03 TB/s of bandwidth.

Q: Do both cards support the same graphics APIs?

A: No. The Arc Pro A60 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The H20 NVL16 lists N/A for DirectX, OpenGL, and Vulkan, reflecting its server-oriented design without display or consumer graphics API support.

Q: What are the power requirements for each card?

A: The Arc Pro A60 has a 130 W TDP and a suggested PSU of 300 W. The H20 NVL16 has a 400 W TDP and a suggested PSU of 800 W.

Q: Which card has a higher boost clock?

A: The H20 NVL16 boosts to 1980 MHz, which is lower than the Arc Pro A60's boost clock of 2050 MHz. However, the H20 NVL16 has a higher base clock at 1830 MHz compared to the Arc Pro A60's 900 MHz.

The Verdict

The data paints a clear picture of two products built for different purposes. The Intel Arc Pro A60 belongs in a workstation context: it has display outputs, consumer graphics API support, and benchmark scores that place it in the 88th percentile of all GPUs. Its performance profile is competitive with, and in some cases slightly ahead of, established workstation and high-end consumer parts. The nearest rival data shows it holding its own against the GeForce RTX 4090, a flagship consumer GPU, with a 0 percent delta in average score. That level of parity, combined with the narrow 2.8 percent spread across its four nearest rivals, indicates a well-balanced performer in its segment.

The NVIDIA H20 NVL16 is a different class of hardware entirely. It has no display outputs, no graphics API support, and no recorded benchmark scores in the database. Its specifications point toward compute density: 9984 shading units, 312 tensor cores, 96 GB of HBM3 memory, and 4.03 TB/s of memory bandwidth. The 6144-bit memory bus and 400 W TDP further confirm a server accelerator role. The 50th percentile ranking, based on zero recorded benchmarks, does not reflect compute capability; it reflects the absence of data in consumer-oriented test suites.

For a buyer selecting a GPU for workstation graphics workloads, the Arc Pro A60 is the only one of the two with the necessary feature set: display connectivity, DirectX 12 Ultimate support, and Vulkan 1.4. For a buyer deploying a server accelerator for memory-intensive compute tasks, the H20 NVL16 offers a memory subsystem that the Arc Pro A60 cannot match, with 8 times the capacity and more than 10 times the bandwidth. The choice is not between two comparable products; it is a choice between two distinct categories, and the database records only one of them with measurable graphics benchmarks.

Specification Differences

The two cards diverge on nearly every major specification field. The Intel Arc Pro A60 uses a 6 nm process from TSMC with 11,500 million transistors on a 269 mm² die, while the NVIDIA H20 NVL16 uses a 5 nm process from TSMC with 80,000 million transistors on an 814 mm² die. Transistor density favors the H20 NVL16 at 98.3M per mm² versus 42.8M per mm² for the Arc Pro A60.

Clock behavior differs substantially. The Arc Pro A60 runs at a 900 MHz base clock and boosts to 2050 MHz. The H20 NVL16 runs at a 1830 MHz base clock and boosts to 1980 MHz. Memory clocks also diverge: the Arc Pro A60 uses 2000 MHz with 16 Gbps effective transfer, while the H20 NVL16 uses 1313 MHz with 5.3 Gbps effective.

Memory capacity and type separate the two completely. The Arc Pro A60 has 12 GB of GDDR6 on a 192-bit bus, yielding 384.0 GB/s of bandwidth. The H20 NVL16 has 96 GB of HBM3 on a 6144-bit bus, yielding 4.03 TB/s of bandwidth. The bus width difference is especially pronounced: 6144 bits versus 192 bits.

Compute unit counts show the H20 NVL16's scale advantage. It has 9984 shading units, 312 TMUs, and 312 tensor cores, while the Arc Pro A60 has 2048 shading units, 128 TMUs, and 16 ray tracing cores. The H20 NVL16 lists no ray tracing core count. Pixel rates favor the Arc Pro A60 at 131.2 GPixel/s versus 47.52 GPixel/s, while texture rates favor the H20 NVL16 at 617.8 GTexel/s versus 262.4 GTexel/s. FP32 throughput is 39.54 TFLOPS for the H20 NVL16 and 8.397 TFLOPS for the Arc Pro A60. FP16 throughput follows the same pattern: 79.07 TFLOPS versus 16.79 TFLOPS.

Power and physical design differ by design intent. The Arc Pro A60 draws 130 W with a 300 W suggested PSU and occupies a single slot. The H20 NVL16 draws 400 W with an 800 W suggested PSU and ships as an SXM module. The Arc Pro A60 uses PCIe 4.0 x16 and provides four DisplayPort 2.0 outputs. The H20 NVL16 uses PCIe 5.0 x16 and provides no display outputs.

Architecture Differences

The architectural gulf between these two GPUs is as wide as their specification gap. The Intel Arc Pro A60 is built on Xe-HPG architecture from the Alchemist generation, specifically the Pro Series. Its chip, the DG2-256, is a graphics-first design with 16 ray tracing cores and support for DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4. The H20 NVL16 is built on NVIDIA's Hopper architecture from the Server Hopper generation, using the GH100 chip. It carries 312 tensor cores, a hallmark of the Hopper design focused on AI and compute acceleration, and lists no graphics API support.

The memory architectures reflect the same divide. The Arc Pro A60 uses conventional GDDR6 memory on a 192-bit bus, a configuration suited to workstation graphics workloads. The H20 NVL16 uses HBM3 on a 6144-bit bus, a stacked memory design intended for high-bandwidth compute access patterns. The 4.03 TB/s bandwidth figure is an order of magnitude beyond the Arc Pro A60's 384.0 GB/s.

Production timelines also differ. The Arc Pro A60 was released on June 5, 2023, while the H20 NVL16 carries a September 1, 2025 release date. The H20 NVL16 lists a predecessor in Server Ada and a successor in Server Blackwell, placing it within a clear server product lineage. The Arc Pro A60 lists no predecessor or successor in the database.

Both GPUs remain in active production status. The Arc Pro A60's smaller die, lower power draw, and display outputs define it as a workstation graphics card. The H20 NVL16's massive die, 400 W power envelope, and absence of display outputs define it as a compute accelerator. The transistor counts alone tell the story of scale: 11,500 million for the Arc Pro A60 versus 80,000 million for the H20 NVL16, a nearly 7-fold difference that corresponds to the cards' drastically different roles in the market.