Intel Arc A380 vs NVIDIA GeForce GTX 960M Comparison

The database comparison between the NVIDIA GeForce GTX 960M and the Intel Arc A380 reveals a decisive generational shift. The recorded data shows the Intel part winning both head-to-head benchmark entries, with margins that are difficult to overstate. This is not a close contest; the A380 appears to operate in a different performance tier altogether.

Head-to-Head Benchmarks

The only directly comparable measurements in the database are the Geekbench OpenCL and Vulkan tests. In Geekbench OpenCL, the Intel Arc A380 scores 38,224 against the GTX 960M’s 11,045. That is a delta of 71.1 percent in favor of the A380, meaning the Intel GPU delivers roughly three and a half times the raw compute throughput in this workload. The gap is even larger in the Vulkan API test: the A380 records 36,736 while the GTX 960M manages just 8,245, a 77.6 percent deficit for the older NVIDIA chip. Both wins belong to the Intel product, and the database shows zero benchmark wins for the GTX 960M in this pairing.

What makes these numbers notable is not just the magnitude but the consistency across two different graphics APIs. OpenCL and Vulkan stress different parts of a GPU’s pipeline, yet the A380’s advantage remains roughly in the same range. This suggests the performance lead is architectural rather than workload-specific. The GTX 960M’s Maxwell architecture, built on a 28 nm process, simply cannot match the throughput of Intel’s Xe-HPG design on 6 nm. The FP32 compute figures in the database reinforce this: the A380 lists 4.198 TFLOPS against the GTX 960M’s 1.505 TFLOPS. Even the pixel and texture rates tell the same story, with the A380 recording 65.60 GPixel/s and 131.2 GTexel/s versus 18.82 GPixel/s and 47.04 GTexel/s for the older card.

The GTX 960M’s average benchmark score across all recorded tests is 9,645, while the A380 sits at 8,558. This is a curious inversion: the newer card wins the head-to-head but has a lower overall average. The explanation lies in the test suites. The A380’s average is dragged down by its Passmark DirectX 10, 11, and 12 results, which are all in the mid-30s, plus a weak Passmark G2D score of 610. The GTX 960M only has two benchmark entries, both Geekbench tests, which happen to be areas where it is relatively less competitive. The percentile rankings reflect this mixed picture: the GTX 960M sits at the 46th percentile of all GPUs, while the A380 is at the 44th. So in the broader database context, neither card is a standout; they are both mid-pack products.

The Verdict

The data points to a simple conclusion for anyone choosing between these two: the Intel Arc A380 is the superior performer in every directly comparable test. The OpenCL and Vulkan deltas are overwhelming, and the A380 also offers more memory (6 GB versus 4 GB), faster memory bandwidth (186.0 GB/s versus 80.19 GB/s), and a more modern feature set including 8 ray tracing cores and DirectX 12 Ultimate support. The GTX 960M’s only advantage in the recorded specifications is its lower transistor density, which is irrelevant to performance, and a smaller die size of 148 mm² versus 157 mm².

However, the GTX 960M is an MXM module, designed for laptops and portable devices, while the A380 is a dual-slot desktop card requiring a PCIe 4.0 x8 slot and a 1x 8-pin power connector. The suggested power supply for the A380 is 250 W. The GTX 960M draws 75 W with no external power connectors. So the choice is not purely about speed; it is about form factor and system compatibility. For a desktop build with a standard PCIe slot and a power supply capable of handling the A380, the Intel card is the obvious pick from the benchmark data. For an older laptop with an MXM slot, the GTX 960M is the only option that physically fits.

FAQ

Q: Which GPU wins in Geekbench OpenCL?

A: The Intel Arc A380 scores 38,224 versus the GTX 960M’s 11,045, a 71.1 percent lead for Intel.

Q: Does the GTX 960M win any benchmark in the head-to-head data?

A: No. The database records zero wins for the GTX 960M; the A380 wins both the OpenCL and Vulkan tests.

Q: How much faster is the A380 in Vulkan?

A: The A380 scores 36,736 against the GTX 960M’s 8,245, which is a 77.6 percent difference in favor of Intel.

Q: What is the average benchmark score for each card?

A: The GTX 960M averages 9,645 across its tests, while the A380 averages 8,558. The A380’s average is lower despite winning the head-to-head because its Passmark scores are very low.

Q: Does the A380 support ray tracing?

A: Yes, the Intel Arc A380 has 8 ray tracing cores. The GTX 960M has none listed in the database.

Q: What is the process node difference?

A: The GTX 960M uses a 28 nm TSMC process, while the A380 uses a 6 nm TSMC process.

Specification Differences

Memory capacity and type differ significantly: the A380 has 6 GB of GDDR6, while the GTX 960M has 4 GB of GDDR5. The memory bus width also diverges, with the A380 using a 96 bit bus and the GTX 960M using 128 bit. Despite the narrower bus, the A380’s memory bandwidth is more than double at 186.0 GB/s versus 80.19 GB/s, thanks to a much higher effective memory clock of 15.5 Gbps against 5 Gbps.

Clock speeds show the A380 running at a 2000 MHz base and 2050 MHz boost, compared to the GTX 960M’s 1097 MHz base and 1176 MHz boost. The compute units scale accordingly: the A380 has 1024 shading units, 64 TMUs, and 32 ROPs, while the GTX 960M has 640 shading units, 40 TMUs, and 16 ROPs. The pixel rate and texture rate are both roughly three times higher on the A380. The bus interface differs as well: the GTX 960M uses MXM-B (3.0), and the A380 uses PCIe 4.0 x8. The A380 requires a 1x 8-pin power connector and suggests a 250 W PSU; the GTX 960M needs no power connectors. The A380 is a dual-slot card with dimensions of 222 mm length, 114 mm height, and 42 mm width; the GTX 960M is an MXM module with no listed dimensions.

Architecture Differences

The GTX 960M is built on NVIDIA’s Maxwell architecture, using the GM107 chip on a 28 nm process from TSMC. It has 1,870 million transistors on a 148 mm² die, giving a transistor density of 12.6 million per mm². The A380 uses Intel’s Xe-HPG architecture, on the DG2-128 chip, fabricated on a 6 nm TSMC process. It packs 7,200 million transistors into a 157 mm² die, achieving a density of 45.9 million per mm². The A380 includes 8 ray tracing cores; the GTX 960M has none. The Intel card also supports DirectX 12 Ultimate (12_2), while the GTX 960M only reaches DirectX 12 (11_0). Both support OpenGL 4.6 and Vulkan 1.4.

The A380’s FP16 performance is listed at 8.397 TFLOPS with a 2:1 ratio, while the GTX 960M has no recorded FP16 capability. The A380’s display outputs are 1x HDMI 2.1 and 3x DisplayPort 2.0, whereas the GTX 960M’s outputs are labeled as portable device dependent. The A380’s predecessor is Xe Graphics, and its successor is Battlemage; the GTX 960M’s predecessor is GeForce 800M, and its successor is GeForce 10 Mobile. Both are end-of-life products, with the GTX 960M released in March 2015 and the A380 in June 2022.

Where Each One Wins

The Intel Arc A380 wins in every measured benchmark category present in the database. Its advantages are most pronounced in compute-heavy workloads like OpenCL and Vulkan, where it leads by 71 to 78 percent. It also wins on memory bandwidth, texture fill rate, pixel fill rate, and raw FP32 throughput. The A380’s ray tracing cores give it a feature that the GTX 960M simply cannot offer. For any modern game or compute task that uses DirectX 12 Ultimate features, the A380 is the only viable choice between these two.

The GTX 960M’s wins are not in performance but in practical deployment. Its MXM form factor, 75 W TDP, and lack of external power connectors make it suitable for portable systems where the A380’s dual-slot, 8-pin PCIe card design would not fit. The GTX 960M also has a smaller die footprint, which may matter in tightly packed chassis. The A380’s higher transistor count and density indicate a much more complex design, but that complexity comes with a power requirement that the GTX 960M avoids. For a laptop user with an existing MXM slot, the GTX 960M remains the functional option, even if its benchmark scores are far lower. For a desktop user with a standard PCIe slot, the data overwhelmingly favors the Intel Arc A380.