Intel Arc Pro A60 vs NVIDIA GeForce RTX 4070 SUPER Comparison

Intel Arc Pro A60 vs NVIDIA GeForce RTX 4070 SUPER is a matchup between a professional-focused Intel GPU and a mainstream NVIDIA GeForce part. The recorded database scores show a decisive overall winner: the RTX 4070 SUPER wins both shared benchmark tests, and by large margins. However, the Arc Pro A60 holds its own in the context of its nearest rivals, and the two cards target different workloads and system constraints. The data indicates that the RTX 4070 SUPER is the stronger performer in raw compute and graphics APIs, while the Arc Pro A60 offers a lower power draw and a different feature set.

Head-to-Head Benchmarks

The only two tests shared between these GPUs in the database are Geekbench OpenCL and Geekbench Vulkan. In both, the NVIDIA GeForce RTX 4070 SUPER decisively outperforms the Intel Arc Pro A60.

In Geekbench OpenCL, the RTX 4070 SUPER scores 172795, while the Arc Pro A60 scores 63485. That is a delta of -63.3% for the Intel part, meaning the NVIDIA card is roughly 2.7 times faster in this compute-oriented test. The margin is enormous and reflects the differences in shading units, texture units, and raw FP32 throughput between the two architectures.

Geekbench Vulkan shows an even wider gap. The RTX 4070 SUPER scores 205624, and the Arc Pro A60 scores 57166. The delta is -72.2%, so the NVIDIA card is about 3.6 times faster. This test stresses the graphics driver and API performance, where NVIDIA’s mature stack and higher clock speeds give it a clear edge.

The head-to-head record is 2 wins for the RTX 4070 SUPER and 0 for the Arc Pro A60. No benchmark in the shared set goes the other way. The NVIDIA card also carries a higher average benchmark score across all its recorded tests: 43223 versus 60326 for the Intel part. That average, however, is influenced by the fact that the Arc Pro A60 has only two benchmark entries, while the RTX 4070 SUPER has ten, including several Passmark tests with very different scoring scales.

It is also worth checking the nearest rival context. The Arc Pro A60 sits at the 88th percentile of all GPUs, with an average benchmark score of 60326. Its nearest rivals include the NVIDIA GeForce RTX 4090 at an average score of 60347 (a delta of 0%), a virtual tie. The AMD Radeon Pro Vega 48 is at 60140 (0.3% slower), and the AMD Radeon PRO V710 is at 58523 (2.8% slower). The Arc Pro A60 is competitive within its own class, despite being far behind the RTX 4070 SUPER.

The RTX 4070 SUPER, by contrast, is at the 83rd percentile, with an average score of 43223. Its nearest rivals are older or mobile parts like the Quadro M6000 24 GB (43262, -0.1%), the RTX 5050 Mobile (43268, -0.1%), and the RTX 4090 Mobile (43667, -1%). The RTX 4070 SUPER’s average is dragged down by several low Passmark scores in legacy DirectX tests (for example, 110 in DirectX 12, 167 in DirectX 10), which are not used for the Arc Pro A60. That skews the comparison, but the head-to-head numbers above are unambiguous.

FAQ

Q: Which GPU has a higher Geekbench Vulkan score?

A: The NVIDIA GeForce RTX 4070 SUPER scores 205624 in Geekbench Vulkan, compared to 57166 for the Intel Arc Pro A60. The NVIDIA card is 72.2% faster in that test.

Q: Are the two GPUs from the same generation?

A: No. The Intel Arc Pro A60 is from the Alchemist (Pro Series) generation, released in 2023, while the NVIDIA GeForce RTX 4070 SUPER is from the GeForce 40 generation, released in 2024. The Intel card is still listed as Active, while the NVIDIA card is End-of-life.

Q: Which GPU has a higher transistor count?

A: The NVIDIA GeForce RTX 4070 SUPER has 35,800 million transistors, which is over three times the 11,500 million found on the Intel Arc Pro A60.

Q: Do both support DirectX 12 Ultimate?

A: Yes, both GPUs list DirectX 12 Ultimate (12_2) as their DirectX version. Both also support OpenGL 4.6 and Vulkan 1.4.

Q: Which card requires a smaller power supply?

A: The Intel Arc Pro A60 has a suggested PSU of 300 W, while the NVIDIA GeForce RTX 4070 SUPER has a suggested PSU of 550 W. The Intel part also has a lower TDP of 130 W versus 220 W for the NVIDIA card.

Q: What is the launch MSRP of the NVIDIA card?

A: The NVIDIA GeForce RTX 4070 SUPER has a launch MSRP of 599 USD. The Intel Arc Pro A60 does not have a launch MSRP recorded in the database.

Architecture Differences

The two GPUs are built on entirely different architectures. The Intel Arc Pro A60 uses Xe-HPG architecture on a chip called DG2-256, part of the Alchemist professional series. The NVIDIA GeForce RTX 4070 SUPER uses Ada Lovelace on the AD104 die. The process nodes differ: Intel is on a 6 nm process from TSMC, while NVIDIA is on a 5 nm process, also from TSMC. The transistor density reflects this: the Intel chip has 42.8 million transistors per square millimeter, while the NVIDIA chip has 121.8 million per square millimeter. The die size is similar, 269 mm² for Intel versus 294 mm² for NVIDIA, but the NVIDIA chip packs 35.8 billion transistors versus 11.5 billion on the Intel chip.

The compute resources are vastly different. The Arc Pro A60 has 2048 shading units, 128 texture mapping units, and 64 ROPs. The RTX 4070 SUPER has 7168 shading units, 224 TMUs, and 80 ROPs. Ray tracing cores: the Intel has 16, the NVIDIA has 56. The NVIDIA also has 224 tensor cores, while the Intel has none listed. The FP32 throughput is 8.397 TFLOPS for the Intel versus 35.48 TFLOPS for the NVIDIA, and the FP16 numbers are 16.79 TFLOPS (2:1 ratio) for Intel versus 35.48 TFLOPS (1:1 ratio) for NVIDIA. Texture and pixel rates follow the same pattern: 262.4 GTexel/s and 131.2 GPixel/s for Intel, versus 554.4 GTEXel/s and 198.0 GPixel/s for NVIDIA.

Memory is a differentiator. Both have 12 GB, but the Intel uses GDDR6 at 2000 MHz (16 Gbps effective) with a 192-bit bus, giving 384.0 GB/s bandwidth. The NVIDIA uses GDDR6X at 1313 MHz (21 Gbps effective) with the same 192-bit bus, giving 504.2 GB/s bandwidth. The PCIe interface is the same: PCIe 4.0 x16.

Display outputs differ: the Intel Arc Pro A60 has 4x DisplayPort 2.0, while the NVIDIA has 1x HDMI 2.1 and 3x DisplayPort 1.4a. The Intel is single-slot, the NVIDIA is dual-slot. The NVIDIA has a 16-pin power connector; the Intel has no power connector listed. The NVIDIA has physical dimensions: 267 mm length, 112 mm height, 42 mm width, while the Intel has none listed.

The Verdict

Based so the recorded data, the NVIDIA GeForce RTX 4070 SUPER is the clear choice for anyone prioritizing raw performance in OpenCL and Vulkan workloads. It wins both head-to-head benchmarks by margins of 63.3% and 72.2%, respectively. The 56 ray tracing cores and 224 tensor cores also give it a feature set for modern AI and ray-traced applications, though no direct RT benchmark is shared in the database.

The Intel Arc Pro A60 is the alternative for scenarios where power draw is a concern. Its 130 W TDP and 300 W suggested PSU are lower than the NVIDIA’s 220 W TDP and 550 W suggested PSU. The single-slot form factor and four DisplayPort 2.0 outputs also target workstation display setups. Within its own peer group, the Arc Pro A60 is competitive: it matches the RTX 4090 in average score (60326 versus 60347, a 0% delta) and beats the AMD Radeon PRO V710 (58657, 2.8% slower). But against the RTX 4070 SUPER, the performance gap is too large to ignore.

For pure compute and graphics performance, the RTX 4070 SUPER wins. For power-constrained or display-heavy professional environments, the Arc Pro A60 is the more practical GPU. The data does not support any scenario where the Intel part outperforms the NVIDIA part in the shared two tests.

Specification Differences

Only the fields that differ between the two GPUs are listed here.

• Chip: Intel DG2-256 vs NVIDIA AD104
• Architecture: Xe-HPG vs Ada Lovelace
• Generation: Alchemist (Pro Series) vs GeForce 40
• Process Node: 6 nm vs 5 nm (both TSMC)
• Transistors: 11,500 million vs 35,800 million
• Die Size: 269 mm² vs 294 mm²
• Transistor Density: 42.8M / mm² vs 121.8M / mm²
• Base Clock: 900 MHz vs 1980 MHz
• Boost Clock: 2050 MHz vs 2475 MHz
• Memory Clock: 2000 MHz (16 Gbps effective) vs 1313 MHz (21 Gbps effective)
• Memory Type: GDDR6 vs GDDR6X
• Memory Bandwidth: 384.0 GB/s vs 504.2 GB/s
• Shading Units: 2048 vs 7168
• TMUs: 128 vs 224
• ROPs: 64 vs 80
• RT Cores: 16 vs 56
• Tensor Cores: None vs 224
• Pixel Rate: 131.2 GPixel/s vs 198.0 GPixel/s
• Texture Rate: 262.4 GTexel/s vs 554.4 GTexel/s
• FP32: 8.397 TFLOPS vs 35.48 TFLOPS
• FP16: 16.79 TFLOPS (2:1) vs 35.48 TFLOPS (1:1)
• TDP: 130 W vs 220 W
• Slot Width: Single-slot vs Dual-slot
• Power Connector: None vs 16-pin
• Suggested PSU: 300 W vs 550 W
• Display Outputs: 4x DisplayPort 2.0 vs 1x HDMI 2.1, 3x DisplayPort 1.4a
• Dimensions: Not listed vs 267 mm x 112 mm x 42 mm
• Production Status: Active vs End-of-life
• Release Date: 2023-06-05 vs 2024-01-16
• Launch MSRP: None vs 599 USD
• Predecessor: None vs GeForce 30
• Successor: None vs GeForce 50

Where Each One Wins

The NVIDIA GeForce RTX 4070 SUPER wins every shared benchmark in the database. In Geekbench OpenCL, it scores 172795 versus 63485 for the Intel, a delta of -63.3%. In Geekbench Vulkan, it scores 205624 versus 57166, a delta of -72.2%. For any user running compute or graphics tasks that rely on these APIs, the RTX 4070 SUPER is the superior part.

The Intel Arc Pro A60 wins in practical design factors. It is a single-slot card with a lower 130 W TDP and a 300 W suggested PSU, which suits compact or multi-GPU workstation builds. It offers four DisplayPort 2.0 outputs, a feature not present on the NVIDIA card, which has one HDMI 2.1 and three DisplayPort 1.4a. The Intel card is also still Active in the database, while the NVIDIA card is End-of-life, meaning the Intel part may have a longer availability window.

In terms of performance, the Intel Arc Pro A60’s nearest rivals include the NVIDIA RTX 4090 (0% delta) and the AMD Radeon Pro W6600M (-2.5% delta), so it is a competitive option within its own class. But against the RTX 4070 SUPER, the data shows no category of shared benchmark where the Intel part wins.

Therefore, the RTX 4070 SUPER is the correct choice for anyone who needs maximum OpenCL or Vulkan performance, and the Intel Arc Pro A60 is the correct choice for those who prioritize low power draw, single-slot form factor, or the specific DisplayPort 2.0 connectivity. The 4070 SUPER’s 83rd percentile and 43223 average score, despite including several weak Passmark DX tests, still place it as a high-performing card, but the head-to-head numbers make the comparison clear.