AMD Instinct MI350X vs Intel Arc Pro A60 Comparison

The AMD Instinct MI350X and Intel Arc Pro A60 occupy entirely different segments of the hardware market, and the recorded data confirms they are not direct competitors. The MI350X is a data-center accelerator with no display outputs and no consumer graphics API support, while the Arc Pro A60 is a professional workstation GPU with full DirectX, OpenGL, and Vulkan support. Benchmark results for the Arc Pro A60 place it at the 88th percentile among all GPUs, with an average score of 60,326, while the MI350X has no recorded benchmarks and sits at the 50th percentile with an average score of zero. The data shows that these two products are designed for fundamentally different workloads, and any comparison must account for that divergence.

Head-to-Head Benchmarks

The head-to-head benchmark table contains no entries, meaning there is no direct measurement comparing the MI350X and Arc Pro A60 in any shared test. However, the database does contain benchmark data for the Arc Pro A60, which allows for meaningful interpretation of its performance standing. The Arc Pro A60 records a Geekbench OpenCL score of 63,485 and a Geekbench Vulkan score of 57,166. These scores contribute to its average benchmark score of 60,326. In contrast, the MI350X has no benchmark entries at all, resulting in an average benchmark score of zero. This absence of data indicates that the MI350X is not evaluated by the same consumer-oriented benchmark suite, which is consistent with its role as an accelerator with no graphics API support.

The nearest rivals for the Arc Pro A60 provide context for its benchmark performance. The NVIDIA GeForce RTX 4090 averages 60,347, which is a delta of 0 percent relative to the Arc Pro A60. The AMD Radeon Pro Vega 48 averages 60,140, placing it 0.3 percent behind the Arc Pro A60. The AMD Radeon Pro W6600M averages 61,896, which is 2.5 percent ahead of the Arc Pro A60. The AMD Radeon PRO V710 averages 58,657, sitting 2.8 percent behind. These deltas show that the Arc Pro A60 performs within a tight band around these rivals, effectively trading positions with the RTX 4090 and the Radeon Pro Vega 48, while trailing the W6600M by a small margin and leading the PRO V710 by a slightly larger one. The data indicates that the Arc Pro A60 delivers competitive compute performance in its professional segment, though the MI350X offers no comparable benchmark data to place alongside it.

For the MI350X, the database lists no wins and no losses in head-to-head benchmarks. Its FP32 throughput is recorded at 72.09 TFLOPS, which is substantially higher than the Arc Pro A60's 8.397 TFLOPS, but this comparison only reflects raw compute specifications, not measured benchmark outcomes. The MI350X also delivers FP16 at 72.09 TFLOPS with a 1:1 ratio, whereas the Arc Pro A60 delivers 16.79 TFLOPS with a 2:1 ratio. These specification differences indicate that the MI350X is built for massive parallel compute tasks, while the Arc Pro A60 focuses on graphics and professional rendering workloads where its 131.2 GPixel/s pixel rate and 262.4 GTexel/s texture rate apply. The absence of shared benchmarks means no direct score comparison is possible, but the architectural data makes the performance orientation of each product clear.

FAQ

Q: What is the average benchmark score for the Intel Arc Pro A60?

A: The Arc Pro A60 has an average benchmark score of 60,326, which places it at the 88th percentile among all GPUs in the database.

Q: Does the AMD Instinct MI350X have any recorded benchmark scores?

A: No, the MI350X has an empty benchmark array, an average benchmark score of zero, and a percentile rank of 50 among all GPUs.

Q: How does the Arc Pro A60 compare to the NVIDIA GeForce RTX 4090 in benchmark scores?

A: The Arc Pro A60 averages 60,326, while the RTX 4090 averages 60,347, resulting in a delta of 0 percent between the two.

Q: What graphics API support does the MI350X offer?

A: The MI350X lists DirectX, OpenGL, and Vulkan as N/A, meaning it has no consumer graphics API support.

Q: What is the memory capacity of each card?

A: The MI350X has 288 GB of HBM3e memory, while the Arc Pro A60 has 12 GB of GDDR6 memory.

Q: Which card has a higher FP32 compute throughput?

A: The MI350X delivers 72.09 TFLOPS of FP32 performance, compared to the Arc Pro A60's 8.397 TFLOPS.

The Verdict

The data supports a clear division of purpose. The AMD Instinct MI350X is a compute accelerator with 72.09 TFLOPS of FP32 throughput, 288 GB of HBM3e memory, and no display outputs. Its 1000 W TDP and OAM Module slot width indicate it is designed for dense data-center deployment, not desktop or workstation use. The Intel Arc Pro A60, with a 130 W TDP, single-slot design, and four DisplayPort 2.0 outputs, is built for professional graphics workstations. Its benchmark percentile of 88 and average score of 60,326 show that it performs competitively against the RTX 4090, the Radeon Pro Vega 48, the Radeon Pro W6600M, and the Radeon PRO V710, with deltas ranging from 2.8 percent behind to 2.5 percent ahead. The MI350X cannot be evaluated on those same benchmarks, so any direct performance verdict is impossible. Instead, the data shows that the MI350X is for compute-heavy AI and scientific workloads, while the Arc Pro A60 is for graphics-centric professional tasks.

Specification Differences

The two cards differ substantially in nearly every measured specification. The MI350X uses a 3 nm process node, while the Arc Pro A60 uses a 6 nm node, both from TSMC. The MI350X contains 185,000 million transistors on a 2380 mm² die, while the Arc Pro A60 contains 11,500 million transistors on a 269 mm² die. Transistor density is 77.7 million per mm² for the MI350X and 42.8 million per mm² for the Arc Pro A60. Clock speeds differ: the MI350X has a base clock of 1000 MHz and a boost clock of 2200 MHz, while the Arc Pro A60 has a base clock of 900 MHz and a boost clock of 2050 MHz. Memory configurations are far apart: the MI350X offers 288 GB of HBM3e on a 8192-bit bus with 8.19 TB/s bandwidth, while the Arc Pro A60 offers 12 GB of GDDR6 on a 192-bit bus with 384.0 GB/s bandwidth. The MI350X has 16,384 shading units and 1,024 TMUs, with zero ROPs and a pixel rate of 0 MPixel/s. The Arc Pro A60 has 2,048 shading units, 128 TMUs, and 64 ROPs, with a pixel rate of 131.2 GPixel/s. Texture rates are 2,252.8 GTexel/s for the MI350X and 262.4 GTexel/s for the Arc Pro A60. Power requirements are also stark: the MI350X has a TDP of 1000 W and a suggested PSU of 1400 W, while the Arc Pro A60 has a TDP of 130 W and a suggested PSU of 300 W. The bus interface is PCIe 5.0 x16 for the MI350X and PCIe 4.0 x16 for the Arc Pro A60. The MI350X has no display outputs, while the Arc Pro A60 has four DisplayPort 2.0 outputs. The MI350X is an OAM Module with no power connectors listed, while the Arc Pro A60 is a single-slot card. Release dates also differ, with the MI350X launching on June 11, 2025, and the Arc Pro A60 on June 5, 2023.

Architecture Differences

The MI350X is built on the CDNA 4.0 architecture with the MI350 256CU chip, while the Arc Pro A60 uses the Xe-HPG architecture with the DG2-256 chip. The MI350X belongs to the Instinct (MIx) generation, whereas the Arc Pro A60 belongs to the Alchemist (Pro Series) generation. The MI350X has no ray tracing cores listed, while the Arc Pro A60 includes 16 ray tracing cores. Neither card lists tensor cores. The MI350X supports FP16 at a 1:1 ratio with FP32, meaning both are 72.09 TFLOPS. The Arc Pro A60 supports FP16 at a 2:1 ratio, delivering 16.79 TFLOPS. The MI350X has no graphics API support, with DirectX, OpenGL, and Vulkan all marked as N/A. The Arc Pro A60 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The MI350X has a predecessor listed as Radeon Instinct, while the Arc Pro A60 has no predecessor listed. The MI350X has a production status that is not listed, while the Arc Pro A60 is marked as Active. These architectural differences confirm that the MI350X is a specialized compute accelerator, while the Arc Pro A60 is a general-purpose professional GPU with full graphics pipeline support.

Where Each One Wins

The MI350X wins in raw compute throughput. Its FP32 output of 72.09 TFLOPS is substantially higher than the Arc Pro A60's 8.397 TFLOPS. Its memory bandwidth of 8.19 TB/s dwarfs the Arc Pro A60's 384.0 GB/s, and its 288 GB memory capacity allows for far larger datasets. The MI350X also has a higher texture rate at 2,252.8 GTexel/s compared to 262.4 GTexel/s. These figures point to workloads involving massive parallel processing, such as AI training or scientific simulation, where memory capacity and bandwidth dominate.

The Arc Pro A60 wins in graphics and display-oriented tasks. It has 64 ROPs and a pixel rate of 131.2 GPixel/s, while the MI350X has zero ROPs and a pixel rate of 0 MPixel/s. The Arc Pro A60 includes 16 ray tracing cores, while the MI350X lists none. The Arc Pro A60 supports DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4, while the MI350X supports none of these APIs. The Arc Pro A60 also provides four DisplayPort 2.0 outputs, while the MI350X has no outputs at all. Its 130 W TDP and single-slot design make it suitable for standard workstation installations, whereas the MI350X requires a 1400 W suggested PSU and an OAM Module form factor. The Arc Pro A60's benchmark percentile of 88 and average score of 60,326 confirm that it performs well in the database's evaluation suite, while the MI350X has no benchmark presence. For any workload that involves rendering, display output, or graphics API usage, the Arc Pro A60 is the only viable option. For compute-only tasks that do not require graphics output, the MI350X offers far larger memory and compute resources. The data does not support a single winner; it supports two separate winners for two separate use cases.