Intel Arc Pro A60 vs NVIDIA RTX A6000 Comparison

Head-to-Head Benchmarks

The database records only two shared benchmark tests between the Intel Arc Pro A60 and the NVIDIA RTX A6000, and both are decisive victories for the NVIDIA card. In Geekbench OpenCL, the RTX A6000 posts a score of 193,937 against the Arc Pro A60’s 63,485, a delta of -67.3% from the Intel card’s perspective. That is not a narrow margin; it is a fundamental gap in raw compute throughput that shows up across the board.

The Vulkan result tells a similar story. The RTX A6000 reaches 164,462 in Geekbench Vulkan, while the Arc Pro A60 manages 57,166, a delta of -65.2%. Again, the NVIDIA card is more than twice as fast in this workload. The Intel GPU does not win either of the two recorded head-to-head tests, giving it zero wins in this comparison, while NVIDIA takes both.

Looking at broader database context, the Arc Pro A60’s average benchmark score is 60,326, which places it at the 88th percentile of all GPUs tracked. Its nearest rival is the NVIDIA GeForce RTX 4090 with an average score of 60,347, a delta of 0%, meaning the Arc Pro A60 is effectively tied with one of the most powerful consumer GPUs in this aggregate metric. The AMD Radeon Pro W6600M scores 61,896, putting it 2.5% ahead of the Intel card, while the AMD Radeon PRO V710 trails at 58,657, which is 2.8% behind. The AMD Radeon Pro Vega 48 sits almost exactly level at 60,140, just 0.3% ahead.

The RTX A6000, by contrast, has an average benchmark score of 44,075, placing it at the 84th percentile. Its nearest rival is the NVIDIA GeForce RTX 4070 Ti at 44,795, which is 1.6% ahead, and the NVIDIA GeForce RTX 4090 Mobile at 43,667, which trails by 0.9%. The NVIDIA Quadro M6000 is 1.8% behind, and the GeForce RTX 5050 Mobile is 1.9% behind.

This creates an interesting inversion. The Arc Pro A60 has a higher aggregate average score than the RTX A6000, despite losing both shared tests by wide margins. The reason is that the database’s average benchmark score pools different test suites, and the Intel card’s results are concentrated in Geekbench tests where it performs relatively well, whereas the RTX A6000 has a much broader set of recorded benchmarks, including Passmark tests that drag its average down. The RTX A6000’s Passmark G3D score of 22,577 and its Passmark GPU Compute score of 14,110 are low relative to its Geekbench results, which lowers its aggregate figure.

Individually, the Geekbench OpenCL delta of -67.3% and the Vulkan delta of -65.2% are the clearest signals. In compute-heavy API workloads, the RTX A6000 dominates. The Intel card’s aggregate percentile is higher, but that is a function of which tests are recorded, not of raw capability in these two shared workloads.

The Verdict

From the recorded data, the NVIDIA RTX A6000 is the clear choice for anyone whose work depends on Geekbench-class OpenCL or Vulkan performance. It is roughly three times faster in OpenCL and nearly three times faster in Vulkan, with deltas of -67.3% and -65.2% respectively. The RTX A6000 also brings 48 GB of GDDR6 memory on a 384-bit bus with 768.0 GB/s of bandwidth, which matters for large datasets and high-resolution rendering workloads that exceed the Arc Pro A60’s 12 GB frame buffer.

The Intel Arc Pro A60, however, holds its own in the aggregate benchmark ranking. Its average score of 60,326 sits at the 88th percentile, above the RTX A6000’s 84th percentile and its 44,075 average. The Intel card is tied with the GeForce RTX 4090 in aggregate scoring, which is a remarkable result for a workstation GPU in this class. It also consumes less power, with a 130 W TDP versus the RTX A6000’s 300 W, and it is a single-slot card, whereas the RTX A6000 requires dual-slot spacing.

Who should pick which? The data suggests that users running applications that rely heavily on OpenCL or Vulkan compute, and who need large memory capacity, should select the RTX A6000. Its 48 GB memory and 768.0 GB/s bandwidth are unmatched by the Intel card. Users who prioritize aggregate benchmark standing, lower power draw, and a slimmer physical footprint may find the Arc Pro A60 more suitable. The Intel card also has a production status of Active in the database, while the RTX A6000 is listed as End-of-life, which could matter for long-term procurement decisions.

The RTX A6000 also offers a launch MSRP of 4,649 USD, which is a notable figure in its specification record. The Arc Pro A60 has no recorded launch MSRP, so no direct price comparison is possible from the data.

For raw compute in the two shared tests, the verdict is unambiguous: NVIDIA wins decisively. For aggregate benchmark performance, the Intel card is surprisingly competitive, and its higher percentile ranking cannot be dismissed. The choice depends on workload emphasis. If the priority is OpenCL or Vulkan throughput and memory capacity, the RTX A6000 is the answer. If the priority is overall benchmark standing, power efficiency, and a single-slot form factor, the Arc Pro A60 is the better fit.

FAQ

Q: Which GPU wins the Geekbench OpenCL test?

A: The NVIDIA RTX A6000 wins with a score of 193,937 against the Intel Arc Pro A60’s 63,485, a delta of -67.3% for the Intel card.

Q: How large is the Vulkan performance gap?

A: The RTX A6000 scores 164,462 in Geekbench Vulkan, while the Arc Pro A60 scores 57,166, a delta of -65.2% in favor of NVIDIA.

Q: Which card has the higher aggregate benchmark score?

A: The Intel Arc Pro A60 has an average benchmark score of 60,326, which places it at the 88th percentile, while the NVIDIA RTX A6000 has an average of 44,075 and sits at the 84th percentile.

Q: How much memory does each card offer?

A: The Intel Arc Pro A60 has 12 GB of GDDR6 memory on a 192-bit bus with 384.0 GB/s bandwidth. The NVIDIA RTX A6000 has 48 GB of GDDR6 memory on a 384-bit bus with 768.0 GB/s bandwidth.

Q: What is the production status of each GPU?

A: The Intel Arc Pro A60 is listed as Active. The NVIDIA RTX A6000 is listed as End-of-life, with its predecessor being Quadro Turing and its successor being Workstation Ada.

Q: Which card has a higher TDP?

A: The NVIDIA RTX A6000 has a 300 W TDP and requires a 700 W suggested PSU, while the Intel Arc Pro A60 has a 130 W TDP and a 300 W suggested PSU.

Specification Differences

The two cards differ across nearly every major specification field in the database. The Intel Arc Pro A60 uses the DG2-256 chip with an 11,500 million transistor count on a 269 mm² die, while the NVIDIA RTX A6000 uses the GA102 chip with 28,300 million transistors on a 628 mm² die. Transistor density is similar, with the Intel chip at 42.8M per mm² and the NVIDIA chip at 45.1M per mm².

Clock speeds differ significantly. The Arc Pro A60 has a base clock of 900 MHz and a boost clock of 2050 MHz. The RTX A6000 runs higher at base, 1410 MHz, but its boost clock is lower at 1800 MHz. Memory clocks are identical at 2000 MHz with 16 Gbps effective speed.

Memory capacity and bandwidth favor NVIDIA heavily. The Arc Pro A60 has 12 GB of GDDR6 on a 192-bit bus with 384.0 GB/s bandwidth. The RTX A6000 has 48 GB of GDDR6 on a 384-bit bus with 768.0 GB/s bandwidth, exactly double the bandwidth.

Compute resources are massively different. The Intel card has 2048 shading units, 128 TMUs, 64 ROPs, and 16 ray tracing cores. The NVIDIA card has 10,752 shading units, 336 TMUs, 112 ROPs, and 84 ray tracing cores. NVIDIA also includes 336 tensor cores, a feature the Intel card does not list. Pixel rate is 131.2 GPixel/s for Intel versus 201.6 GPixel/s for NVIDIA. Texture rate is 262.4 GTexel/s versus 604.8 GTexel/s. FP32 throughput is 8.397 TFLOPS versus 38.71 TFLOPS. FP16 performance is 16.79 TFLOPS with a 2:1 ratio for Intel, versus 38.71 TFLOPS with a 1:1 ratio for NVIDIA.

Power and physical specifications differ as well. The Arc Pro A60 has a 130 W TDP, is single-slot, and requires a 300 W suggested PSU. The RTX A6000 has a 300 W TDP, is dual-slot, uses an 8-pin EPS power connector, and requires a 700 W suggested PSU. The RTX A6000 has recorded dimensions of 267 mm in length (10.5 inches) and 112 mm in height (4.4 inches); the Intel card has no recorded dimensions.

Display outputs differ in standard: the Intel card offers 4x DisplayPort 2.0, while the NVIDIA card offers 4x DisplayPort 1.4a. Both use PCIe 4.0 x16. Release dates are far apart, with the RTX A6000 launching on 2020-10-04 and the Arc Pro A60 on 2023-06-05.

Architecture Differences

The architectural split is fundamental. Intel’s Arc Pro A60 is built on the Xe-HPG architecture, part of the Alchemist generation in the Pro Series. It uses a 6 nm process from TSMC. NVIDIA’s RTX A6000 is built on the Ampere architecture, part of the Workstation Ampere generation, using an 8 nm process from Samsung. The process node advantage goes to Intel, which is reflected in the smaller die size of 269 mm² versus 628 mm² for NVIDIA, despite the NVIDIA chip carrying nearly 2.5 times more transistors.

The compute architecture diverges in how FP16 is handled. The Intel card operates FP16 at a 2:1 ratio relative to FP32, meaning it processes half-precision at roughly twice the rate of full precision. The NVIDIA card operates FP16 at a 1:1 ratio, meaning its FP16 throughput is equal to its FP32 throughput. This is a meaningful difference for workloads that rely on half-precision math, as NVIDIA’s approach provides more balanced throughput.

Ray tracing hardware is present on both, but in very different quantities. The Arc Pro A60 has 16 ray tracing cores, while the RTX A6000 has 84. Tensor cores are exclusive to the NVIDIA card, with 336 units, which enables AI-accelerated workloads that the Intel card does not list support for in the database.

API support is identical on paper: both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The display output standard differs, with Intel using DisplayPort 2.0 and NVIDIA using DisplayPort 1.4a, which affects maximum supported display resolutions and refresh rates.

The memory subsystem differs not just in capacity but in bus width and resulting bandwidth. Intel uses a 192-bit bus, NVIDIA uses a 384-bit bus. Both use GDDR6 memory at the same effective speed, but the wider bus gives NVIDIA double the bandwidth. This has direct implications for memory-bound workloads such as large texture sets, high-resolution framebuffers, and compute tasks that stream data through memory.

Production status is another architectural lifecycle marker. The Arc Pro A60 is Active, while the RTX A6000 is End-of-life, with a predecessor of Quadro Turing and a successor of Workstation Ada. The release timing, nearly three years apart, reflects two different points in each company’s product roadmap.