Intel Arc A770 vs Intel Arc Pro A60 Comparison

The Intel Arc A770 and Intel Arc Pro A60 are both built on Intel’s Xe-HPG architecture and the Alchemist generation, yet they target very different performance tiers. The A770 is a consumer-focused, end-of-life flagship with a full DG2-512 die, while the A60 is an active professional card based on the smaller DG2-256 chip. The benchmark data reveals a clear hierarchy, but the Pro A60’s design priorities—efficiency and a compact single-slot form factor—tell a different story than raw compute.

Head-to-Head Benchmarks

The most direct comparison comes from the two shared benchmark workloads: Geekbench OpenCL and Geekbench Vulkan. In both cases, the Intel Arc A770 wins decisively, taking all 2 head-to-head contests with a 0-win record for the Arc Pro A60.

In the Geekbench OpenCL test, the A770 scores 109,175 against the A60’s 63,485. That is a 72% advantage for the A770. This gap is substantial and reflects the massive difference in raw compute resources between the two cards. The A770’s FP32 throughput is 19.66 TFLOPS, while the A60 delivers 8.397 TFLOPS—the A770 is more than twice as fast in theoretical floating-point performance, which directly correlates with the observed OpenCL result.

The Vulkan workload shows a similar pattern, though the margin narrows slightly. The A770 posts 94,284, while the A60 manages 57,166. The delta here is 64.9% in favor of the A770. Vulkan’s lower-level API can sometimes reduce driver overhead, but the sheer hardware disparity remains dominant. The A770’s 4,096 shading units and 256 TMUs dwarf the A60’s 2,048 shading units and 128 TMUs, explaining why the A770 maintains such a commanding lead across both API tests.

Looking at the average benchmark scores, the A770 sits at 68,809, while the A60 averages 60,326. The A770’s average is 14.1% higher. However, this aggregate metric includes the A770’s 3DMark Steel Nomad DX12 score of 2,969, which is a workload the A60 does not have a recorded result for. This makes the average comparison less direct than the shared Geekbench tests, but it still positions the A770 firmly ahead in overall compute capability.

The percentile rankings reinforce this. The A770 is in the 90th percentile of all GPUs, while the A60 is in the 88th percentile. Despite the large performance lead in the head-to-head tests, the percentile difference is only 2 points, suggesting that the A60’s efficiency and professional optimization keep it competitive within its own segment.

Where Each One Wins

The Intel Arc A770 wins in every benchmark category where both cards have data. Its dual wins in OpenCL and Vulkan make it the clear choice for general-purpose compute and graphics workloads that leverage these APIs. The 72% lead in OpenCL is particularly notable, as this API is often used in content creation, scientific computing, and AI inference tasks. The A770’s 16 GB of GDDR6 memory on a 256-bit bus provides 512.0 GB/s of bandwidth, which is 33.3% more than the A60’s 384.0 GB/s. This memory advantage is critical for large datasets and high-resolution textures, further cementing the A770’s dominance in memory-intensive applications.

The Arc Pro A60, despite losing the head-to-head, has its own strengths that are not captured in the benchmark suite. Its 130 W TDP is 42.2% lower than the A770’s 225 W, making it a far more power-efficient option. The A60 is also a single-slot card with no external power connectors, whereas the A770 is a dual-slot design requiring a 6-pin and an 8-pin connector. For dense workstation builds or systems with strict power and space constraints, the A60’s physical design is a significant advantage. It also offers 4x DisplayPort 2.0 outputs compared to the A770’s 1x HDMI 2.1 and 3x DisplayPort 2.0, giving it more multi-display flexibility out of the box.

In terms of production status, the A60 is active and currently available, while the A770 is end-of-life. This means the A60 is the one with ongoing support and availability, which matters for professional deployments where long-term reliability is paramount.

FAQ

Q: Which card has a higher Geekbench OpenCL score?

A: The Intel Arc A770 scores 109,175 in Geekbench OpenCL, which is 72% higher than the Intel Arc Pro A60’s 63,485.

Q: What is the difference in Vulkan performance between the two cards?

A: The A770 achieves 94,284 in Geekbench Vulkan, while the A60 scores 57,166. The A770 leads by 64.9%.

Q: How do the average benchmark scores compare?

A: The A770 has an average benchmark score of 68,809, while the A60 averages 60,326. This puts the A770 approximately 14.1% ahead on average.

Q: Which GPU has a higher memory bandwidth?

A: The Intel Arc A770 has a memory bandwidth of 512.0 GB/s, compared to the Intel Arc Pro A60’s 384.0 GB/s. The A770’s bandwidth is 33.3% higher.

Q: Are both cards based on the same architecture?

A: Yes, both cards use the Xe-HPG architecture and belong to the Alchemist generation, but they use different dies: the A770 uses DG2-512, while the A60 uses DG2-256.

Q: What is the power consumption difference?

A: The A770 has a TDP of 225 W, while the A60 has a TDP of 130 W. The A60 consumes 42.2% less power.

Specification Differences

The two cards diverge significantly across nearly every major specification. The Intel Arc A770 uses the larger DG2-512 chip, while the Intel Arc Pro A60 uses the DG2-256 die. This leads to a major transistor count difference: the A770 packs 21,700 million transistors on a 406 mm² die, whereas the A60 has 11,500 million transistors on a 269 mm² die. The A770’s transistor density is 53.4 million per mm², slightly higher than the A60’s 42.8 million per mm².

Clock speeds also differ substantially. The A770 has a base clock of 2100 MHz and a boost clock of 2400 MHz. The A60’s base clock is much lower at 900 MHz, with a boost clock of 2050 MHz. This 1200 MHz difference in base clock is a major factor in the performance gap.

Memory configurations are distinct. The A770 features 16 GB of GDDR6 on a 256-bit bus, yielding 512.0 GB/s of bandwidth. The A60 has 12 GB of GDDR6 on a 192-bit bus, providing 384.0 GB/s. Both use 2000 MHz memory with 16 Gbps effective speed, but the wider bus on the A770 gives it the bandwidth advantage.

Compute resources are doubled on the A770: 4,096 shading units, 256 TMUs, 128 ROPs, and 32 RT cores versus 2,048 shading units, 128 TMUs, 64 ROPs, and 16 RT cores on the A60. This results in the A770’s 19.66 TFLOPS FP32 and 39.32 TFLOPS FP16 (2:1) performance, compared to the A60’s 8.397 TFLOPS FP32 and 16.79 TFLOPS FP16 (2:1).

Physical and power characteristics differ as well. The A770 is a dual-slot card with a 225 W TDP, requiring a 6-pin and 8-pin power connector and a 550 W suggested PSU. The A60 is a single-slot card with a 130 W TDP, no external power connectors, and a 300 W suggested PSU. Display outputs also vary: the A770 has 1x HDMI 2.1 and 3x DisplayPort 2.0, while the A60 has 4x DisplayPort 2.0.

Architecture Differences

Both cards are built on the Xe-HPG architecture using a 6 nm process at TSMC, but they represent different tiers of the Alchemist generation. The A770 is from the Arc 7 series, while the A60 is from the Pro Series. The A770’s DG2-512 chip is the full implementation of the architecture, whereas the A60’s DG2-256 is a cut-down version with half the shading units, TMUs, ROPs, and RT cores.

The cache hierarchy is not detailed, but the difference in die size—406 mm² versus 269 mm²—indicates a substantially larger memory subsystem and execution engine on the A770. The A770 also has a predecessor (Xe Graphics) and a successor (Battlemage), marking it as a transitional product. The A60 has no listed predecessor or successor, reflecting its role as a standalone professional offering.

Both cards support the same API set: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. This means feature-level parity in terms of software support, despite the hardware differences. The PCIe interface is identical at PCIe 4.0 x16 for both.

The A60’s lower base clock of 900 MHz versus the A770’s 2100 MHz is notable. This suggests the A60 is tuned for efficiency rather than peak performance, which aligns with its professional positioning where sustained workloads and thermal management are critical.

The Verdict

The data is unambiguous: the Intel Arc A770 outperforms the Intel Arc Pro A60 in every measured benchmark. With a 72% lead in OpenCL and a 64.9% lead in Vulkan, the A770 is the superior choice for raw compute and graphics performance. Its higher average benchmark score of 68,809 versus 60,326, along with its 90th percentile ranking, confirms it as the more powerful GPU.

However, the choice is not purely about speed. The Arc Pro A60’s 130 W TDP, single-slot design, and lack of external power connectors make it a far more practical option for compact or power-constrained systems. Its active production status ensures ongoing availability, unlike the end-of-life A770. The A60 also offers four DisplayPort outputs, which could be a deciding factor for multi-monitor professional setups.

For users who prioritize maximum performance and have the power budget and physical space, the Arc A770 is the obvious pick. Its 16 GB memory, higher bandwidth, and doubled compute resources deliver a decisive advantage in compute-heavy workloads. For those who need a professional-grade card that fits in tight spaces, draws less power, and is still actively produced, the Arc Pro A60 is the rational choice, despite its lower benchmark scores. The data does not support the A60 as a performance alternative, but its design philosophy and lifecycle status present a compelling case for specific use cases.