Intel Arc Pro A60 vs NVIDIA GeForce RTX 4070 Ti Comparison

Head-to-Head Benchmarks

The benchmark data shows a decisive advantage for the NVIDIA GeForce RTX 4070 Ti in every recorded head-to-head test. In Geekbench OpenCL, the RTX 4070 Ti scores 176,953 against the Intel Arc Pro A60’s 63,485, a delta of -64.1% from the Intel card’s perspective. That means the NVIDIA card delivers roughly 2.8 times the OpenCL compute throughput in this specific workload. The gap widens further in Geekbench Vulkan: the RTX 4070 Ti posts 213,808 while the Arc Pro A60 manages 57,166, a -73.3% delta. In this test, the NVIDIA card is about 3.7 times faster.

These two results are the only direct comparisons available in the database, and both go to NVIDIA. The Arc Pro A60’s average benchmark score across all recorded tests is 60,326, which places it in the 88th percentile of all GPUs. The RTX 4070 Ti, by contrast, averages 44,795 across its broader test suite, sitting in the 84th percentile. The apparent contradiction between the head-to-head results and the average scores is explained by the different test sets: the Arc Pro A60’s average is drawn from only two Geekbench runs, while the RTX 4070 Ti’s average includes PassMark DirectX 9 through 12, G2D, G3D, GPU compute, and 3DMark Steel Nomad DX12. On raw compute tests like Geekbench Vulkan, the NVIDIA card is overwhelmingly faster, but the RTX 4070 Ti’s overall average is dragged down by older DirectX API benchmarks where it scores relatively low (e.g., 187 in DirectX 10, 116 in DirectX 12, 352 in DirectX 9).

Looking at nearest rivals for context, the Arc Pro A60 sits within 0% of the NVIDIA GeForce RTX 4090 (60,347 vs. 60,326), which is remarkable for a workstation card with a 130 W TDP. It also trails the AMD Radeon Pro W6600M by 2.5% (61,896 vs. 60,326) and leads the AMD Radeon PRO V710 by 2.8% (58,657 vs. 60,326). The RTX 4070 Ti, meanwhile, is nearly tied with the RTX 5090 Mobile (45,152, -0.8%), sits 1.3% behind the AMD Radeon Pro 5500 XT (45,384), and leads the RTX A6000 by 1.6% (44,075). These proximity scores indicate that both cards occupy specific performance tiers, but the head-to-head tests are unambiguous: the RTX 4070 Ti wins both compute contests by massive margins.

Architecture Differences

The two cards are built on fundamentally different architectures and process nodes. The Intel Arc Pro A60 uses the DG2-256 chip based on Xe-HPG architecture, from the Alchemist generation (Pro Series). It is fabricated on a 6 nm process at TSMC, with 11,500 million transistors on a 269 mm² die, yielding a transistor density of 42.8 million per mm². The NVIDIA GeForce RTX 4070 Ti uses the AD104 chip based on Ada Lovelace, from the GeForce 40 generation, on a 5 nm TSMC process with 35,800 million transistors on a 294 mm² die, giving a density of 121.8 million per mm². The NVIDIA chip packs over three times the transistor count into a slightly larger die, reflecting a much denser design.

Core counts differ sharply. The Arc Pro A60 has 2,048 shading units, 128 texture mapping units, and 64 ROPs, plus 16 ray tracing cores and no dedicated tensor cores. The RTX 4070 Ti fields 7,680 shading units, 240 TMUs, and 80 ROPs, along with 60 RT cores and 240 tensor cores. That is 3.75 times the shading units, 1.875 times the TMUs, and 1.25 times the ROPs. The FP32 compute rating reflects this: the Arc Pro A60 delivers 8.397 TFLOPS, while the RTX 4070 Ti delivers 40.09 TFLOPS. FP16 performance is 16.79 TFLOPS (2:1 ratio) for the Intel card versus 40.09 TFLOPS (1:1 ratio) for NVIDIA, meaning the RTX 4070 Ti does not halve throughput for half-precision work.

Memory configurations share the same 12 GB capacity and 192-bit bus width, but the type and bandwidth diverge. The Arc Pro A60 uses GDDR6 at 16 Gbps effective, yielding 384.0 GB/s. The RTX 4070 Ti uses GDDR6X at 21 Gbps effective, yielding 504.2 GB/s, a 31% bandwidth advantage. Clock speeds also differ: the Intel card runs at 900 MHz base and 2050 MHz boost, while the NVIDIA card runs at 2310 MHz base and 2610 MHz boost. Pixel rate is 131.2 GPixel/s for the Arc Pro A60 versus 208.8 GPixel/s for the RTX 4070 Ti, and texture rate is 262.4 GTexel/s versus 626.4 GTexel/s.

Power and physical design contrast heavily. The Arc Pro A60 has a 130 W TDP, is single-slot, and has no listed power connector, with a suggested PSU of 300 W. The RTX 4070 Ti has a 285 W TDP, is dual-slot, requires a 16-pin connector, and suggests a 600 W PSU. The NVIDIA card is longer at 285 mm (11.2 inches) versus a null length for the Intel card, but the RTX 4070 Ti’s height is 112 mm (4.4 inches) and width 42 mm (1.7 inches). Display outputs also differ: the Arc Pro A60 offers 4x DisplayPort 2.0, while the RTX 4070 Ti offers 1x HDMI 2.1 and 3x DisplayPort 1.4a. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Intel card is listed as Active production status, released June 5, 2023, while the RTX 4070 Ti is End-of-life, released January 2, 2023, with a launch MSRP of 799 USD.

The Verdict

Based strictly on the recorded data, the NVIDIA GeForce RTX 4070 Ti is the superior performer in every direct comparison. It wins both Geekbench OpenCL and Vulkan by margins of 64.1% and 73.3%, respectively. Its FP32 compute is nearly five times higher (40.09 vs. 8.397 TFLOPS), its memory bandwidth is 31% higher (504.2 vs. 384.0 GB/s), and its texture rate is more than double (626.4 vs. 262.4 GTexel/s). For any workload that relies on raw compute throughput, ray tracing (60 RT cores vs. 16), or tensor operations (240 tensor cores vs. none), the RTX 4070 Ti is the clear choice.

The Arc Pro A60, however, has its own strengths. It is far more power-efficient on paper: 130 W TDP versus 285 W, and a suggested PSU of 300 W versus 600 W. It is single-slot versus dual-slot, which matters for dense workstation builds. It also offers DisplayPort 2.0 outputs, which the NVIDIA card lacks. Its average benchmark score of 60,326 versus 44,795 for the RTX 4070 Ti suggests that in the specific tests the Intel card was subjected to, it performs at a higher percentile of all GPUs (88th vs. 84th). But that is an artifact of test selection, not a real performance equivalence.

For a user prioritizing compute performance above all else, the RTX 4070 Ti wins outright. For a user prioritizing low power draw, single-slot form factor, and modern display connectivity in a professional environment, the Arc Pro A60 offers a compelling package, especially given its proximity to the RTX 4090 in average score (60,326 vs. 60,347, 0% delta). The data does not support calling the Intel card “better” in any compute benchmark; it supports calling it “more efficient” and “more compact.”

FAQ

Q: Which card wins in Geekbench OpenCL?

A: The NVIDIA GeForce RTX 4070 Ti wins with a score of 176,953 versus the Intel Arc Pro A60’s 63,485, a delta of -64.1% from the Intel card.

Q: How large is the Vulkan performance gap?

A: The RTX 4070 Ti scores 213,808 in Geekbench Vulkan, while the Arc Pro A60 scores 57,166, a delta of -73.3%.

Q: Do both cards have the same memory capacity?

A: Yes, both have 12 GB, but the RTX 4070 Ti uses GDDR6X with 504.2 GB/s bandwidth, while the Arc Pro A60 uses GDDR6 with 384.0 GB/s.

Q: What is the TDP difference?

A: The Arc Pro A60 has a 130 W TDP, while the RTX 4070 Ti has a 285 W TDP. The suggested PSU is 300 W for Intel and 600 W for NVIDIA.

Q: Which card has more ray tracing cores?

A: The RTX 4070 Ti has 60 RT cores, while the Arc Pro A60 has 16 RT cores.

Q: Is the Arc Pro A60 still in production?

A: Yes, the Intel card is listed as Active production status, while the RTX 4070 Ti is listed as End-of-life.

Where Each One Wins

Intel Arc Pro A60 wins on: power efficiency (130 W vs. 285 W), slot occupancy (single-slot vs. dual-slot), display outputs (4x DisplayPort 2.0 vs. 1x HDMI 2.1 + 3x DisplayPort 1.4a), and average benchmark percentile (88th vs. 84th). Its average score of 60,326 puts it within 0% of the RTX 4090’s 60,347, indicating strong relative performance in its tested workloads. It also has a lower suggested PSU requirement (300 W vs. 600 W), making it more suitable for constrained power environments.

NVIDIA GeForce RTX 4070 Ti wins on: every direct benchmark (OpenCL and Vulkan), FP32 compute (40.09 vs. 8.397 TFLOPS), FP16 compute (40.09 vs. 16.79 TFLOPS), memory bandwidth (504.2 vs. 384.0 GB/s), texture rate (626.4 vs. 262.4 GTexel/s), pixel rate (208.8 vs. 131.2 GPixel/s), shading units (7,680 vs. 2,048), TMUs (240 vs. 128), ROPs (80 vs. 64), RT cores (60 vs. 16), tensor cores (240 vs. 0), and boost clock (2610 vs. 2050 MHz). It also has a higher base clock (2310 vs. 900 MHz) and a larger die with higher transistor density (121.8M vs. 42.8M per mm²).

Use-case split: For gaming, rendering, or compute-heavy tasks like machine learning inference, the RTX 4070 Ti is the only choice from this data. For professional workstation environments where space is at a premium, power budgets are tight, or DisplayPort 2.0 is required for high-refresh-rate monitors, the Arc Pro A60 provides a viable alternative, especially given its active production status and lower TDP. The RTX 4070 Ti’s end-of-life status may matter for long-term procurement, but its performance lead is overwhelming in all recorded metrics.