AMD Radeon RX 9060 XT LP vs Intel Arc A770 Comparison

Head-to-Head Benchmarks

The benchmark data offers a clear, if lopsided, picture in the two directly comparable compute workloads. In Geekbench OpenCL, the Intel Arc A770 scores 109,175 against the AMD Radeon RX 9060 XT LP’s 88,183. That is a 23.8% advantage for Intel, a substantial margin that places the A770 in a different performance tier for raw GPU compute tasks. The gap becomes a canyon in Geekbench Vulkan: Intel scores 94,284 while AMD manages just 39,476. The delta here is a staggering 138.8% — the Arc A770 more than doubles the Radeon’s result in this API. This is not a marginal win; it is a decisive sweep across both available head-to-head tests.

The aggregate benchmark scores tell a slightly different but complementary story. The Arc A770’s average benchmark score is 68,809, placing it in the 90th percentile of all GPUs. The RX 9060 XT LP averages 63,830, sitting at the 89th percentile. While the gap narrows to roughly 7.8% in these aggregate terms, the individual test deltas reinforce that Intel’s card is the stronger performer in the measured scenarios. Notably, the Arc A770’s nearest rival is the NVIDIA CMP 90HX at 69,000 (a -0.3% delta), while the RX 9060 XT LP sits essentially tied with the NVIDIA CMP 30HX at 63,842 (a 0% delta). The Intel card competes in a higher performance bracket overall, despite both GPUs landing within a single percentile point of each other in the global ranking.

It is worth emphasizing that the Vulkan result is the single most striking data point in the comparison. A 138.8% lead in Vulkan suggests architectural efficiency in that API that AMD’s offering cannot match, at least in this benchmark implementation. The OpenCL result, while less extreme, still shows Intel holding a comfortable edge. With 2 wins for Intel and 0 for AMD in the head-to-head set, the data does not support any scenario where the Radeon takes the lead in these specific workloads.

Where Each One Wins

Given the head-to-head results, the Intel Arc A770 is the clear winner in compute-oriented benchmarks. The OpenCL score of 109,175 indicates strong general-purpose GPU compute performance, useful for workloads like rendering, physics simulation, or data processing that leverage this API. The Vulkan score of 94,284 further cements its position for graphics workloads that use Vulkan, where it outperforms the RX 9060 XT LP by a factor of more than two. For users prioritizing these specific metrics, the Arc A770 is the only rational choice between the two.

The AMD Radeon RX 9060 XT LP does not win any benchmark in the provided data. However, its profile suggests different strengths that are not captured in the head-to-head tests. Its lower power envelope — 140 W TDP versus 225 W for Intel — and its active production status indicate it is designed for scenarios where efficiency and availability matter more than raw compute throughput. The RX 9060 XT LP’s 89th percentile ranking versus Intel’s 90th is nearly equivalent, but the Radeon achieves this with a significantly lower power draw. The data does not include gaming benchmarks, ray tracing tests, or power efficiency metrics, so any claim of a win for AMD in those areas would be speculation. Based strictly on the numbers, Intel wins every measured test, while AMD’s advantages lie outside the benchmark suite provided — namely in power consumption and product lifecycle.

The aggregate scores further contextualize this split. The Arc A770’s 68,809 average places it alongside professional-grade cards like the AMD Radeon Pro WX 8200 (69,870, -1.5% delta) and NVIDIA Quadro P6000 (69,986, -1.7% delta). The RX 9060 XT LP’s 63,830 average aligns it with mid-range offerings like the AMD Radeon RX 7600M (63,775, +0.1% delta) and AMD Radeon Pro Vega 56 (63,693, +0.2% delta). This indicates that Intel’s card competes in a higher performance tier, while AMD’s LP (low-profile) variant targets a more modest performance class, likely prioritizing physical size and thermal constraints over peak compute.

Architecture Differences

The two GPUs represent fundamentally different architectural approaches. Intel’s Arc A770 uses the DG2-512 chip built on the Xe-HPG architecture, part of the Alchemist generation (Arc 7). AMD’s RX 9060 XT LP uses the Navi 44 chip on RDNA 4.0 architecture, from the Navi IV generation (RX 9000 series). These are not iterative updates of each other; they are divergent designs from different manufacturers targeting different trade-offs.

The manufacturing process highlights a key difference. Intel uses a 6 nm process at TSMC, while AMD uses a 4 nm process, also at TSMC. The newer node gives AMD a significant transistor density advantage: 149.2 million transistors per square millimeter versus Intel’s 53.4 million per mm². This allows AMD to pack 29,700 million transistors onto a 199 mm² die, while Intel fits 21,700 million onto a much larger 406 mm² die. The RX 9060 XT LP is less than half the physical size of the Arc A770, yet contains 37% more transistors. This density disparity explains why AMD can achieve competitive aggregate performance with far fewer execution units.

The compute architecture differs radically. The Arc A770 has 4,096 shading units, 256 TMUs, and 128 ROPs, along with 32 ray tracing cores. The RX 9060 XT LP has 2,048 shading units, 128 TMUs, and 64 ROPs, also with 32 ray tracing cores. Despite having half the shader count, AMD’s card achieves higher FP32 throughput: 24.99 TFLOPS versus Intel’s 19.66 TFLOPS. This is due to the higher boost clock of 3,050 MHz on AMD versus 2,400 MHz on Intel, combined with architectural efficiency. The FP16 numbers are telling: Intel delivers 39.32 TFLOPS (2:1 ratio to FP32), while AMD delivers 24.99 TFLOPS (1:1 ratio). This means Intel’s card has dedicated or accelerated FP16 paths that double its throughput, whereas AMD treats FP16 and FP32 identically. For workloads using FP16, Intel has a massive theoretical advantage.

Memory architecture also diverges. Both cards have 16 GB of GDDR6, but Intel uses a 256-bit bus providing 512.0 GB/s bandwidth, while AMD uses a 128-bit bus providing 322.3 GB/s. Intel’s bandwidth advantage is 37% higher. However, AMD’s memory runs at 20.1 Gbps effective versus Intel’s 16 Gbps, partially compensating for the narrower bus. The RX 9060 XT LP also supports PCIe 5.0 x16, while the Arc A770 uses PCIe 4.0 x16, giving AMD twice the theoretical system interface bandwidth.

Specification Differences

The specifications where these two cards differ are extensive. The process node differs: 6 nm for Intel versus 4 nm for AMD. Transistor counts differ significantly: 21,700 million versus 29,700 million. Die size is nearly inverse: 406 mm² for Intel versus 199 mm² for AMD. Transistor density is 53.4M per mm² versus 149.2M per mm² — a 2.8x difference.

Clock speeds vary dramatically. Intel’s base clock is 2,100 MHz with a boost of 2,400 MHz. AMD’s base clock is 1,380 MHz, but it boosts to 3,050 MHz with a game clock of 2,450 MHz. The boost clocks differ by 650 MHz in AMD’s favor, which is substantial. Memory clocks also differ: Intel runs at 2,000 MHz (16 Gbps effective), while AMD runs at 2,518 MHz (20.1 Gbps effective).

Compute unit counts differ: 4,096 shading units, 256 TMUs, and 128 ROPs for Intel versus 2,048 shading units, 128 TMUs, and 64 ROPs for AMD. Pixel rate is 307.2 GPixel/s for Intel versus 195.2 GPixel/s for AMD. Texture rate is 614.4 GTexel/s versus 390.4 GTexel/s. FP32 is 19.66 TFLOPS versus 24.99 TFLOPS. FP16 is 39.32 TFLOPS (2:1) versus 24.99 TFLOPS (1:1). TDP is 225 W versus 140 W. Power connectors are 1x 6-pin + 1x 8-pin for Intel versus a single 8-pin for AMD. Suggested PSU is 550 W versus 300 W. Bus interface is PCIe 4.0 x16 versus PCIe 5.0 x16. Display outputs are 1x HDMI 2.1 + 3x DisplayPort 2.0 for Intel versus 1x HDMI 2.1b + 2x DisplayPort 2.1a for AMD. Production status is End-of-life versus Active. Release dates are 2022-10-11 versus 2025-12-16. The Arc A770 has a launch MSRP of 329 USD; the RX 9060 XT LP has no listed launch MSRP. Memory bandwidth is 512.0 GB/s versus 322.3 GB/s. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API support is identical.

FAQ

Q: Which GPU wins the most benchmarks in the head-to-head comparison?

A: The Intel Arc A770 wins both available head-to-head tests. It leads in Geekbench OpenCL with 109,175 versus 88,183 (a 23.8% delta) and in Geekbench Vulkan with 94,284 versus 39,476 (a 138.8% delta). The win count is 2 for Intel and 0 for AMD.

Q: How do the aggregate benchmark scores compare between the two cards?

A: The Intel Arc A770 has an average benchmark score of 68,809, placing it in the 90th percentile of all GPUs. The AMD Radeon RX 9060 XT LP averages 63,830, placing it in the 89th percentile. Intel’s nearest rival is the NVIDIA CMP 90HX at 69,000, while AMD’s nearest rival is the NVIDIA CMP 30HX at 63,842.

Q: What are the key architectural differences between the two GPUs?

A: The Intel Arc A770 uses the DG2-512 chip on Xe-HPG architecture (Alchemist generation), built on a 6 nm process. The AMD RX 9060 XT LP uses the Navi 44 chip on RDNA 4.0 architecture (Navi IV generation), built on a 4 nm process. AMD’s die is 199 mm² versus Intel’s 406 mm², yet AMD packs 29,700 million transistors versus Intel’s 21,700 million, giving AMD a 149.2M per mm² density versus Intel’s 53.4M per mm².

Q: How do the FP32 and FP16 throughput figures differ?

A: The AMD RX 9060 XT LP has higher FP32 throughput at 24.99 TFLOPS versus the Intel Arc A770’s 19.66 TFLOPS. However, the Intel card has higher FP16 throughput at 39.32 TFLOPS (2:1 ratio to FP32), while AMD delivers 24.99 TFLOPS FP16 (1:1 ratio to FP32). This gives Intel a significant theoretical advantage for FP16 workloads.

Q: What is the memory configuration difference?

A: Both cards have 16 GB of GDDR6 memory, but the Intel Arc A770 uses a 256-bit bus with 512.0 GB/s bandwidth, while the AMD RX 9060 XT LP uses a 128-bit bus with 322.3 GB/s bandwidth. Intel’s bandwidth advantage is notable, despite AMD’s higher effective memory speed of 20.1 Gbps versus Intel’s 16 Gbps.

Q: What are the power and interface differences?

A: The Intel Arc A770 has a 225 W TDP with a suggested PSU of 550 W and uses 1x 6-pin + 1x 8-pin power connectors. The AMD RX 9060 XT LP has a 140 W TDP with a suggested PSU of 300 W and uses a single 8-pin connector. Intel uses PCIe 4.0 x16, while AMD uses PCIe 5.0 x16. The RX 9060 XT LP is also an active product, while the Arc A770 is end-of-life.