Intel Arc Pro A60 vs NVIDIA GeForce RTX 4090 Comparison

The RTX 4090 and Arc Pro A60 sit at opposite ends of the GPU spectrum, yet their average benchmark scores are nearly identical—60,347 for the NVIDIA flagship versus 60,326 for Intel’s entry-level pro card, a delta of 0%. This statistical tie in overall average is misleading; the two cards achieve that parity through completely different benchmark profiles, with the RTX 4090 dominating compute-heavy workloads while the Arc Pro A60 holds its own in legacy rasterization tests. The data shows a head-to-head that is less about raw speed and more about workload specialization.

Head-to-Head Benchmarks

The only direct comparisons available are Geekbench compute tests, and they are not close. In Geekbench OpenCL, the RTX 4090 scores 255,416 against the Arc Pro A60’s 63,485, a 302.3% advantage for NVIDIA. That is a 4x performance gap in raw compute throughput, reflecting the massive difference in shading units, memory bandwidth, and FP32 output.

The Vulkan result is even more lopsided. The RTX 4090 posts 271,631, while the Arc Pro A60 manages 57,166—a 375.2% delta. This indicates NVIDIA’s architecture handles the lower-level API with far greater efficiency, likely due to its larger cache hierarchy and more mature driver stack for Vulkan workloads.

However, the average benchmark scores tell a different story. The RTX 4090’s average of 60,347 is dragged down by its Passmark DirectX results: 224 in DX10, 326 in DX11, 150 in DX12, and 397 in DX9. The Arc Pro A60 does not have published Passmark scores in the data, so its average is derived solely from its two Geekbench entries. This means the RTX 4090’s Passmark G3D score of 38,194 and GPU compute score of 26,613 are part of its average, while the A60’s average relies entirely on its 63,485 OpenCL and 57,166 Vulkan numbers. The net effect is that both cards land in the 88th percentile of all GPUs, but for opposite reasons—NVIDIA wins on sheer horsepower, Intel wins on consistency across its limited test set.

Architecture Differences

The architectural gap is enormous. The RTX 4090 uses the AD102 chip on TSMC’s 5 nm node, packing 76,300 million transistors into a 609 mm² die with a transistor density of 125.3M per mm². The Arc Pro A60 uses the DG2-256 chip on TSMC’s 6 nm node, with just 11,500 million transistors on a 269 mm² die at 42.8M per mm². That is a 6.6x difference in transistor count and a 2.3x difference in die area.

Clocks also diverge sharply. The RTX 4090 runs at a 2235 MHz base and 2520 MHz boost, while the Arc Pro A60 sits at 900 MHz base and 2050 MHz boost. The NVIDIA card’s higher base clock is particularly notable, as it sustains performance even under load without relying solely on boost behavior.

Memory subsystems are in different leagues. The RTX 4090 has 24 GB of GDDR6X on a 384-bit bus, delivering 1.01 TB/s of bandwidth. The Arc Pro A60 has 12 GB of GDDR6 on a 192-bit bus, yielding 384.0 GB/s. The RTX 4090’s memory clock is listed at 1313 MHz with 21 Gbps effective, while the A60 runs at 2000 MHz with 16 Gbps effective—the NVIDIA card’s wider bus more than compensates for its lower memory clock.

Shader resources are equally unbalanced. The RTX 4090 has 16,384 shading units, 512 TMUs, 176 ROPs, 128 RT cores, and 512 tensor cores. The Arc Pro A60 has 2,048 shading units, 128 TMUs, 64 ROPs, and 16 RT cores, with no tensor core count listed. This translates to 82.58 TFLOPS FP32 for NVIDIA versus 8.397 TFLOPS for Intel—a 9.8x gap. The RTX 4090 also has a 1:1 FP16 ratio at 82.58 TFLOPS, while the A60’s FP16 is 16.79 TFLOPS at a 2:1 ratio.

Power and physical design differ just as much. The RTX 4090 is a 450 W triple-slot card requiring an 850 W PSU and a single 16-pin connector. The Arc Pro A60 is a 130 W single-slot card with a 300 W PSU recommendation and no external power connector listed. The RTX 4090 measures 304 mm long, 137 mm tall, and 61 mm wide; the A60 has no dimensions listed, but its single-slot form factor implies a much smaller footprint.

Where Each One Wins

The RTX 4090 wins every head-to-head benchmark by a wide margin, but that is only half the story. Its wins are in OpenCL and Vulkan, which are compute-oriented APIs. The 302.3% OpenCL lead and 375.2% Vulkan lead make it the clear choice for GPU compute tasks like rendering, simulation, or machine learning inference—workloads that leverage the 512 tensor cores and 82.58 TFLOPS FP32 output.

The Arc Pro A60’s strength is not in raw compute but in its efficiency and footprint. It delivers 88th percentile performance with a 130 W TDP, meaning it can run in systems where a 450 W card would be impractical. Its 4x DisplayPort 2.0 outputs are a notable feature; the RTX 4090 offers 1x HDMI 2.1 and 3x DisplayPort 1.4a, so the A60 supports more modern display connections for multi-monitor pro setups.

The data also shows the A60’s average score is competitive because its two Geekbench results are high relative to its hardware. Its OpenCL score of 63,485 is roughly 25% of the RTX 4090’s, which is impressive given the 9.8x FP32 gap. This suggests Intel’s architecture is efficient at converting its limited shader count into practical compute throughput, at least in these specific tests.

Specification Differences

| Specification | RTX 4090 | Arc Pro A60 |

|---|---|---|

| Process node | 5 nm | 6 nm |

| Transistors | 76,300 million | 11,500 million |

| Die size | 609 mm² | 269 mm² |

| Base clock | 2235 MHz | 900 MHz |

| Boost clock | 2520 MHz | 2050 MHz |

| Memory size | 24 GB | 12 GB |

| Memory type | GDDR6X | GDDR6 |

| Memory bus | 384 bit | 192 bit |

| Memory bandwidth | 1.01 TB/s | 384.0 GB/s |

| Shading units | 16,384 | 2,048 |

| TMUs | 512 | 128 |

| ROPs | 176 | 64 |

| RT cores | 128 | 16 |

| Tensor cores | 512 | None listed |

| FP32 | 82.58 TFLOPS | 8.397 TFLOPS |

| FP16 | 82.58 TFLOPS (1:1) | 16.79 TFLOPS (2:1) |

| TDP | 450 W | 130 W |

| Slot width | Triple-slot | Single-slot |

| Power connectors | 1x 16-pin | None listed |

| Suggested PSU | 850 W | 300 W |

| Display outputs | 1x HDMI 2.1, 3x DisplayPort 1.4a | 4x DisplayPort 2.0 |

| Release date | 2022-09-19 | 2023-06-05 |

| Production status | End-of-life | Active |

| Launch MSRP | 1,599 USD | None listed |

FAQ

Q: Which card has a higher average benchmark score?

A: The RTX 4090 averages 60,347, while the Arc Pro A60 averages 60,326—a 0% delta, meaning they are effectively tied.

Q: How much faster is the RTX 4090 in Vulkan?

A: The RTX 4090 scores 271,631 versus 57,166 for the Arc Pro A60, a 375.2% advantage.

Q: Does the Arc Pro A60 have tensor cores?

A: No tensor core count is listed for the Arc Pro A60; the RTX 4090 has 512 tensor cores.

Q: What is the memory bandwidth difference?

A: The RTX 4090 offers 1.01 TB/s, while the Arc Pro A60 provides 384.0 GB/s.

Q: Which card requires a larger power supply?

A: The RTX 4090 suggests an 850 W PSU; the Arc Pro A60 suggests a 300 W PSU.

Q: Are both cards in the same performance percentile?

A: Yes, both are in the 88th percentile of all GPUs.

The Verdict

The data is unambiguous for raw performance: the RTX 4090 wins every head-to-head test with at least a 302.3% margin. If your workload is compute-bound—OpenCL, Vulkan, or anything that uses FP32 or tensor operations—the RTX 4090 is the only choice from these two. Its 82.58 TFLOPS FP32 and 512 tensor cores are in a different class from the A60’s 8.397 TFLOPS and absent tensor core count.

The Arc Pro A60 is not competitive on speed, but it wins on practicality. Its 130 W TDP, single-slot design, and 4x DisplayPort 2.0 outputs make it a better fit for dense multi-GPU workstations or systems with strict power and space limits. It also has an active production status, while the RTX 4090 is end-of-life. If you need a card today for light pro compute and modern display connectivity, the A60 is serviceable. If you need maximum compute performance regardless of power or size, the RTX 4090 is the data-backed winner—just be prepared for its 450 W draw and triple-slot footprint. The 88th percentile ranking for both cards masks a fundamental divide: the RTX 4090 is a performance monster, and the Arc Pro A60 is an efficiency specialist. Pick based on your power budget, not the average scores.