Intel Arc A380 vs NVIDIA GeForce GTX 1660 Ti Comparison

Where Each One Wins

The benchmark results paint a clear split between these two cards. The Intel Arc A380 takes a single decisive victory, while the NVIDIA GeForce GTX 1660 Ti dominates everything else. That one Intel win, however, is not a minor detail: it is a 530.4% advantage in Geekbench Vulkan, a massive outlier that shows the Arc A380's driver and hardware stack handles Vulkan workloads exceptionally well. If your primary application is Vulkan-based, the A380 is the only rational choice from this data.

The GTX 1660 Ti, by contrast, wins 9 out of 10 head-to-head tests. It leads across DirectX 9, 10, 11, and 12 titles, OpenCL compute, 2D graphics, and the 3DMark Steel Nomad DX12 test. The margins vary from a modest 23.8% in Steel Nomad to a crushing 63.1% in PassMark DirectX 11. This is not a subtle advantage; the GTX 1660 Ti is faster in nearly every measurable category, and in several cases it is more than twice as fast.

For a builder choosing between these two, the decision hinges on workload. If you live in Vulkan applications, the Arc A380's 36,736 Geekbench Vulkan score versus the GTX 1660 Ti's 5,827 is the single most important number in this comparison. For anything else, the GTX 1660 Ti is the safer, faster pick. The recorded data does not support using the A380 for legacy DirectX titles, compute tasks, or general 3D rendering; it only supports a Vulkan-focused use case.

FAQ

Q: Which card is better for DirectX 11 gaming?

A: The GTX 1660 Ti wins decisively. In PassMark DirectX 11, the GTX 1660 Ti scores 103 versus the Arc A380's 38, a 63.1% lead. That is the largest margin in any DirectX test.

Q: Does the Arc A380 beat the GTX 1660 Ti in any benchmark?

A: Yes, in Geekbench Vulkan. The Arc A380 scores 36,736, and the GTX 1660 Ti scores 5,827. That is a 530.4% advantage for the Intel card, which is the only test the A380 wins.

Q: How do these cards compare in raw 3D performance?

A: The GTX 1660 Ti is far ahead. In PassMark G3D, the GTX 1660 Ti scores 12,871 versus 6,252 for the Arc A380, a 51.4% difference. In 3DMark Steel Nomad DX12, the GTX 1660 Ti scores 1,061 versus 808, a 23.8% lead.

Q: Which card is better for compute workloads?

A: The GTX 1660 Ti. In Geekbench OpenCL, it scores 51,029 versus 38,224 for the Arc A380, a 25.1% advantage. In PassMark GPU Compute, the GTX 1660 Ti scores 5,226 versus 2,762, a 47.1% lead.

Q: What about older DirectX 9 games?

A: The GTX 1660 Ti is dramatically faster. It scores 190 in PassMark DirectX 9, while the Arc A380 scores 73, a 61.6% difference. The A380 is not competitive for legacy DirectX titles.

Q: Are these cards similar in overall standing among all GPUs?

A: They are close in percentile ranking. The Arc A380 sits at the 44th percentile, and the GTX 1660 Ti sits at the 41st percentile. However, the GTX 1660 Ti has a higher average benchmark score of 7,723 versus 8,558 for the Arc A380, which is notable given the A380's percentile is higher due to its Vulkan outlier.

Head-to-Head Benchmarks

The most striking result is Geekbench Vulkan. The Arc A380 posts 36,736, and the GTX 1660 Ti posts 5,827. The delta is 530.4% in favor of Intel. This is not a marginal edge; it is a complete inversion of the expected order. If any workload in your stack is Vulkan-heavy, the A380 will crush the GTX 1660 Ti.

Every other benchmark flips the script. In 3DMark Steel Nomad DX12, the GTX 1660 Ti scores 1,061 against 808 for the Arc A380, a 23.8% lead. That is the closest DirectX result between them, and it still favors NVIDIA clearly.

The PassMark suite shows the real spread. In DirectX 9, the GTX 1660 Ti scores 190 versus 73, a 61.6% advantage. In DirectX 10, it scores 66 versus 37, a 43.9% lead. In DirectX 11, the gap widens to 63.1% (103 versus 38). In DirectX 12, the GTX 1660 Ti still leads by 31.4% (51 versus 35). Every legacy API test is a landslide for NVIDIA.

Compute results follow the same pattern. Geekbench OpenCL gives the GTX 1660 Ti a 25.1% edge (51,029 versus 38,224). PassMark GPU Compute shows a 47.1% gap (5,226 versus 2,762). Even 2D graphics favor the GTX 1660 Ti: PassMark G2D scores 804 versus 610, a 24.1% lead.

The overall PassMark G3D score, which aggregates general 3D performance, is 12,871 for the GTX 1660 Ti and 6,252 for the Arc A380. That is a 51.4% difference. The only category where the A380 does not lose is Vulkan, and there it wins by an order of magnitude.

Specification Differences

The two cards differ in almost every core specification. The Arc A380 uses a 6 nm process, while the GTX 1660 Ti uses a 12 nm node. Intel's chip packs 7,200 million transistors on a 157 mm² die, giving a transistor density of 45.9M per mm². NVIDIA's TU116 has 6,600 million transistors on a 284 mm² die, with a density of 23.2M per mm². The Arc A380 is far denser and smaller.

Clock speeds also diverge. The Arc A380 runs at a 2000 MHz base and 2050 MHz boost. The GTX 1660 Ti runs at 1500 MHz base and 1770 MHz boost. Intel's card is clocked higher, but that does not translate into faster performance in the recorded benchmarks.

Memory configurations are similar in size but different in bandwidth. Both have 6 GB of GDDR6. The Arc A380 uses a 96-bit bus with 186.0 GB/s bandwidth, while the GTX 1660 Ti uses a 192-bit bus with 288.0 GB/s bandwidth. The NVIDIA card has 54.8% more memory bandwidth, which helps explain its compute and DirectX leads.

The GPU cores differ significantly. The Arc A380 has 1,024 shading units, 64 TMUs, 32 ROPs, and 8 ray tracing cores. The GTX 1660 Ti has 1,536 shading units, 96 TMUs, and 48 ROPs, with no dedicated ray tracing cores. The GTX 1660 Ti has 50% more shading units, 50% more TMUs, and 50% more ROPs. The A380's ray tracing hardware is unique, but the benchmark data does not show a ray tracing test.

Pixel and texture rates reflect the core counts. The Arc A380 delivers 65.60 GPixel/s and 131.2 GTexel/s. The GTX 1660 Ti delivers 84.96 GPixel/s and 169.9 GTexel/s. FP32 compute is 4.198 TFLOPS for the A380 and 5.437 TFLOPS for the GTX 1660 Ti. FP16 is 8.397 TFLOPS and 10.87 TFLOPS respectively.

Power draw differs substantially. The Arc A380 has a 75 W TDP, and the GTX 1660 Ti has a 120 W TDP. Both use one 8-pin connector, but the suggested PSU is 250 W for the A380 and 300 W for the GTX 1660 Ti. The A380 is the more efficient card by wattage, though the benchmark data does not include power efficiency measurements.

The bus interface and display outputs also differ. The A380 uses PCIe 4.0 x8, while the GTX 1660 Ti uses PCIe 3.0 x16. The A380 outputs 1x HDMI 2.1 and 3x DisplayPort 2.0, while the GTX 1660 Ti has 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a.

Architecture Differences

The Arc A380 is built on Intel's Xe-HPG architecture, specifically the DG2-128 chip, and belongs to the Alchemist generation under the Arc 3 lineup. It supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The GTX 1660 Ti uses NVIDIA's Turing architecture with the TU116 chip, in the GeForce 16 generation. It supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The API difference matters: the A380 supports the full 12_2 feature set, while the GTX 1660 Ti is capped at 12_1.

The A380 includes 8 ray tracing cores; the GTX 1660 Ti has none. Neither card has tensor cores. The A380's process node is 6 nm versus 12 nm, and it uses a much denser transistor layout. The A380 also has double the memory clock in effective Gbps (15.5 Gbps versus 12 Gbps), but the narrower bus limits its bandwidth.

Release timing differs. The A380 launched on 2022-06-13, and the GTX 1660 Ti launched on 2019-02-21. Both are end-of-life. The A380's predecessor is Xe Graphics, and its successor is Battlemage. The GTX 1660 Ti's predecessor is GeForce 10, and its successor is GeForce 20.

The Verdict

The data is unambiguous. The GTX 1660 Ti wins 9 of 10 head-to-head benchmarks, with leads ranging from 23.8% to 63.1% across DirectX, OpenCL, and general 3D tests. Its average benchmark score is 7,723, and it sits at the 41st percentile. The Arc A380 averages 8,558 and sits at the 44th percentile, but that average is inflated by a single Vulkan result.

If you are building a system for Vulkan applications, the Arc A380 is the pick. Its 36,736 Geekbench Vulkan score versus 5,827 for the GTX 1660 Ti is a 530.4% difference, and no other benchmark in this comparison comes close to that margin. The A380 also draws less power at 75 W versus 120 W, which matters for small form factor builds.

For everything else, choose the GTX 1660 Ti. It is faster in DirectX 9, 10, 11, and 12, faster in OpenCL compute, faster in 2D graphics, and faster in overall 3D performance. The 51.4% lead in PassMark G3D is the most representative single metric for general gaming. The GTX 1660 Ti also has 288.0 GB/s of memory bandwidth versus 186.0 GB/s, which supports its dominance in bandwidth-sensitive workloads.

There is no scenario in the recorded data where the Arc A380 wins except Vulkan. If that is your target, buy Intel. If it is not, buy NVIDIA. The decision is that simple, and the benchmark results do not leave room for nuance.