Intel Arc Pro A60 vs NVIDIA GeForce RTX 5070 SUPER Comparison

The Intel Arc Pro A60 and NVIDIA GeForce RTX 5070 SUPER occupy different corners of the GPU market, and the recorded benchmark data confirms that their performance profiles are far from comparable in any direct sense. The Arc Pro A60, built on Intel’s Xe-HPG architecture, posts an average benchmark score of 60,326 across its two recorded tests, while the RTX 5070 SUPER, based on Blackwell 2.0, records an average of 2,690 from a single test. This massive gap in average scores, however, does not tell the whole story, as the two cards are measured with entirely different workloads in the database. The Arc Pro A60 delivers 8.397 TFLOPS of FP32 compute and 384.0 GB/s of memory bandwidth, while the RTX 5070 SUPER delivers 32.15 TFLOPS and 672.0 GB/s. The data indicates a clear separation in raw capability, but the nature of the benchmarks and the intended use cases for each card require careful interpretation.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark results between the Intel Arc Pro A60 and the NVIDIA GeForce RTX 5070 SUPER. Instead, each card was evaluated under different test suites, and the scores reflect distinct performance domains. The Arc Pro A60 shows a Geekbench OpenCL score of 63,485 and a Geekbench Vulkan score of 57,166, which together produce its average of 60,326. The RTX 5070 SUPER shows a 3DMark Steel Nomad DX12 score of 2,690, which alone defines its average of 2,690. These figures cannot be compared numerically across test types, but they position each card firmly within its respective performance tier.

Looking at the nearest rivals in the database clarifies where each card stands. The Arc Pro A60 sits at the 88th percentile among all GPUs, with its average score of 60,326 landing within 0% of the NVIDIA GeForce RTX 4090’s 60,347. That is a near-perfect match in average score, and the delta of 0.3% relative to the AMD Radeon Pro Vega 48’s 60,140 places the Arc Pro A60 effectively alongside some of the strongest accelerators in the database. The Arc Pro A60 also trails the AMD Radeon Pro W6600M by 2.5% (that card averages 61,896) and leads the AMD Radeon PRO V710 by 2.8% (which averages 58,657). These deltas are small, suggesting that the Arc Pro A60 is a highly consistent performer in its benchmark class, competing within a few percentage points of much more expensive or specialized hardware.

The RTX 5070 SUPER, by contrast, sits at the 18th percentile among all GPUs, with an average score of 2,690. Its nearest rivals are all lower-end parts: the NVIDIA Quadro K1100M (2,664, delta 1%), the NVIDIA GeForce GT 1030 (2,662, delta 1.1%), the Intel Arc Pro B50 (2,660, delta 1.1%), and the NVIDIA GeForce GT 440 (2,645, delta 1.7%). The RTX 5070 SUPER leads this group by only 1% to 1.7%, a narrow margin that suggests the recorded 3DMark Steel Nomad DX12 score does not reflect the card’s full hardware potential. The raw specs in the database show a far more powerful GPU, so the low percentile is likely an artifact of the single benchmark used, not a statement about the card’s overall capability.

Architecture Differences

The two GPUs are built on fundamentally different architectures and process technologies. The Intel Arc Pro A60 uses the DG2-256 chip, which is based on the Xe-HPG architecture and belongs to the Alchemist Pro Series generation. It is fabricated on a 6 nm process at TSMC, with 11,500 million transistors packed into a 269 mm² die, yielding a transistor density of 42.8 million per square millimeter. The NVIDIA GeForce RTX 5070 SUPER uses the GB205 chip, based on the Blackwell 2.0 architecture and belonging to the GeForce 50 generation. It is fabricated on a 5 nm process at TSMC, with 31,100 million transistors on a 263 mm² die, for a transistor density of 118.3 million per square millimeter. The RTX 5070 SUPER therefore crams nearly three times as many transistors into a slightly smaller die, a direct result of the denser 5 nm node.

Core configurations differ dramatically. The Arc Pro A60 has 2,048 shading units, 128 texture mapping units, 64 render output units, and 16 ray tracing cores. The RTX 5070 SUPER has 6,400 shading units, 200 texture mapping units, 80 render output units, 50 ray tracing cores, and 200 tensor cores. The RTX 5070 SUPER has no direct tensor core counterpart listed for the Arc Pro A60, which reports null for that field. The shading unit count alone is more than triple on the NVIDIA side, and the ray tracing core count is more than triple as well. These differences translate directly into throughput: the Arc Pro A60 delivers 8.397 TFLOPS of FP32 and 16.79 TFLOPS of FP16 (at a 2:1 ratio), while the RTX 5070 SUPER delivers 32.15 TFLOPS of FP32 and 32.15 TFLOPS of FP16 (at a 1:1 ratio). The NVIDIA card’s FP16 throughput matches its FP32 throughput, indicating a different compute design philosophy.

Memory subsystems also diverge. The Arc Pro A60 uses 12 GB of GDDR6 on a 192 bit bus, achieving a bandwidth of 384.0 GB/s. The RTX 5070 SUPER uses 18 GB of GDDR7 on a 192 bit bus, achieving a bandwidth of 672.0 GB/s. Both cards use the same bus width, but the newer GDDR7 memory and higher effective speed of 28 Gbps versus 16 Gbps give the NVIDIA card 75% more bandwidth. Clock behavior differs as well: the Arc Pro A60 runs at a base of 900 MHz and a boost of 2050 MHz, while the RTX 5070 SUPER runs at a base of 2325 MHz and a boost of 2512 MHz. The NVIDIA card starts at a base clock higher than Intel’s boost clock, which contributes to its higher pixel and texture rates: 201.0 GPixel/s and 502.4 GTexel/s for the RTX 5070 SUPER, versus 131.2 GPixel/s and 262.4 GTexel/s for the Arc Pro A60.

Power and physical design also separate the two. The Arc Pro A60 has a TDP of 130 W and a suggested power supply of 300 W, and it fits in a single-slot design. The RTX 5070 SUPER has a TDP of 275 W, uses a single 16 pin power connector, and occupies a dual-slot design with dimensions of 245 mm by 115 mm by 40 mm. The Arc Pro A60 lists no dimensions and no power connector details in the database. Interface support differs: the Arc Pro A60 uses PCIe 4.0 x16 and outputs 4x DisplayPort 2.0, while the RTX 5070 SUPER uses PCIe 5.0 x16 and outputs 1x HDMI 2.1b and 3x DisplayPort 2.1b. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API coverage is identical.

FAQ

Q: Which card has a higher average benchmark score?

A: The Intel Arc Pro A60 has an average benchmark score of 60,326, while the NVIDIA GeForce RTX 5070 SUPER has an average of 2,690. The Arc Pro A60 also ranks at the 88th percentile among all GPUs, whereas the RTX 5070 SUPER ranks at the 18th percentile.

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

A: The Arc Pro A60 averages 60,326, which is within 0% of the NVIDIA GeForce RTX 4090’s 60,347, 0.3% ahead of the AMD Radeon Pro Vega 48’s 60,140, 2.5% behind the AMD Radeon Pro W6600M’s 61,896, and 2.8% ahead of the AMD Radeon PRO V710’s 58,657.

Q: How does the NVIDIA GeForce RTX 5070 SUPER compare to its nearest rivals?

A: The RTX 5070 SUPER averages 2,690, which is 1% ahead of the NVIDIA Quadro K1100M’s 2,664, 1.1% ahead of the NVIDIA GeForce GT 1030’s 2,662, 1.1% ahead of the Intel Arc Pro B50’s 2,660, and 1.7% ahead of the NVIDIA GeForce GT 440’s 2,645.

Q: What are the memory specifications of each card?

A: The Arc Pro A60 has 12 GB of GDDR6 memory on a 192 bit bus, with a bandwidth of 384.0 GB/s. The RTX 5070 SUPER has 18 GB of GDDR7 memory on a 192 bit bus, with a bandwidth of 672.0 GB/s.

Q: What are the power requirements for each card?

A: The Arc Pro A60 has a TDP of 130 W and a suggested power supply of 300 W. The RTX 5070 SUPER has a TDP of 275 W, uses a 1x 16 pin power connector, and lists no suggested power supply in the database.

Q: Which card has more compute throughput?

A: The RTX 5070 SUPER delivers 32.15 TFLOPS of FP32 and 32.15 TFLOPS of FP16, while the Arc Pro A60 delivers 8.397 TFLOPS of FP32 and 16.79 TFLOPS of FP16. The RTX 5070 SUPER has nearly four times the FP32 throughput.

Specification Differences

The two cards differ across nearly every specification field in the database. The Arc Pro A60 uses the DG2-256 chip with Xe-HPG architecture, while the RTX 5070 SUPER uses the GB205 chip with Blackwell 2.0 architecture. The process node is 6 nm for Intel and 5 nm for NVIDIA, both at TSMC. Transistor counts are 11,500 million for the Arc Pro A60 and 31,100 million for the RTX 5070 SUPER, with die sizes of 269 mm² and 263 mm² respectively. Transistor density is 42.8 million per square millimeter on Intel versus 118.3 million on NVIDIA.

Clock speeds differ substantially: the Arc Pro A60 runs at 900 MHz base and 2050 MHz boost, while the RTX 5070 SUPER runs at 2325 MHz base and 2512 MHz boost. Memory clocks are 16 Gbps effective for the Intel card and 28 Gbps effective for the NVIDIA card. Memory capacity is 12 GB GDDR6 versus 18 GB GDDR7, with bandwidths of 384.0 GB/s and 672.0 GB/s. Shading units are 2,048 versus 6,400, TMUs are 128 versus 200, ROPs are 64 versus 80, and RT cores are 16 versus 50. The RTX 5070 SUPER has 200 tensor cores, while the Arc Pro A60 lists none. Pixel rates are 131.2 GPixel/s versus 201.0 GPixel/s, and texture rates are 262.4 GTexel/s versus 502.4 GTexel/s. FP32 is 8.397 TFLOPS versus 32.15 TFLOPS, and FP16 is 16.79 TFLOPS versus 32.15 TFLOPS.

TDP values are 130 W versus 275 W, slot widths are single-slot versus dual-slot, and power connectors are unspecified for Intel but 1x 16 pin for NVIDIA. The suggested PSU is 300 W for Intel and null for NVIDIA. Bus interfaces are PCIe 4.0 x16 versus PCIe 5.0 x16. Display outputs are 4x DisplayPort 2.0 versus 1x HDMI 2.1b and 3x DisplayPort 2.1b. Physical dimensions are listed only for the RTX 5070 SUPER: 245 mm length, 115 mm height, and 40 mm width. Release dates are June 5, 2023 for the Arc Pro A60 and December 31, 2025 for the RTX 5070 SUPER. Both cards share the same API support for DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4.

Where Each One Wins

The Intel Arc Pro A60 wins in the database’s compute-oriented benchmarks. Its Geekbench OpenCL score of 63,485 and Geekbench Vulkan score of 57,166 place it at the 88th percentile, and its average sits within 0% of the NVIDIA GeForce RTX 4090, a result that indicates strong general-purpose compute performance. The Arc Pro A60 also wins on power efficiency in terms of TDP, drawing only 130 W compared to 275 W for the RTX 5070 SUPER, and it requires a smaller 300 W power supply suggestion. Its single-slot design gives it an advantage in dense or compact installations where space is constrained.

The NVIDIA GeForce RTX 5070 SUPER wins on raw hardware specifications across the board. It has more shading units, TMUs, ROPs, ray tracing cores, tensor cores, and memory capacity, and it produces higher pixel and texture rates. Its FP32 throughput of 32.15 TFLOPS is nearly four times the Arc Pro A60’s 8.397 TFLOPS, and its FP16 throughput of 32.15 TFLOPS is nearly double the Arc Pro A60’s 16.79 TFLOPS. The RTX 5070 SUPER also has a higher memory bandwidth of 672.0 GB/s versus 384.0 GB/s, and its 18 GB of GDDR7 memory exceeds the Arc Pro A60’s 12 GB of GDDR6. The RTX 5070 SUPER supports PCIe 5.0 x16, while the Arc Pro A60 is limited to PCIe 4.0 x16.

In terms of benchmark standing, the Arc Pro A60 wins on percentile and average score, but the RTX 5070 SUPER’s single 3DMark Steel Nomad DX12 result of 2,690 belongs to a different workload category. The Arc Pro A60’s rivals in the database are high-end compute cards, while the RTX 5070 SUPER’s rivals are older or lower-tier parts, which suggests the recorded test for the NVIDIA card does not exercise its full feature set. The RTX 5070 SUPER also wins on memory type and speed, using GDDR7 at 28 Gbps effective versus GDDR6 at 16 Gbps effective.

The Verdict

The data points to a clear split in intended use. The Intel Arc Pro A60, with its 88th percentile ranking, average score of 60,326, and proximity to the NVIDIA GeForce RTX 4090 in average score, is positioned as a capable compute-oriented card. Its lower TDP of 130 W, single-slot footprint, and 300 W suggested power supply make it suitable for environments where power and space are limited. The RTX 5070 SUPER, despite its 18th percentile ranking and single benchmark score of 2,690, carries hardware specifications that far exceed the Arc Pro A60: 32.15 TFLOPS of FP32, 672.0 GB/s of bandwidth, 18 GB of GDDR7, and 6,400 shading units. The low percentile is a function of the benchmark used, not a reflection of the card’s theoretical peak.

For users who prioritize compute workloads measured by OpenCL and Vulkan, the Arc Pro A60 shows stronger recorded results and a higher standing among all GPUs. For users who prioritize raw throughput, memory bandwidth, and modern features such as tensor cores and PCIe 5.0, the RTX 5070 SUPER is the more capable part on paper. The absence of head-to-head benchmarks means the two cards cannot be directly ranked against each other in the database, and the nearest rival lists confirm that they compete in different performance strata. The Arc Pro A60 belongs alongside workstation-class accelerators, while the RTX 5070 SUPER’s specifications place it in a higher performance tier that the recorded 3DMark result does not capture. Each card wins where its strengths are measured: the Arc Pro A60 in compute benchmarks and efficiency, the RTX 5070 SUPER in raw specification superiority.