Intel Arc A380 vs NVIDIA GeForce GTX 675MX Comparison

Intel Arc A380 decisively outperforms the NVIDIA GeForce GTX 675MX in the single overlapping benchmark, posting a Geekbench OpenCL score of 38,224 versus 10,723, a margin of 256.5% in favor of the Intel card. The Arc A380 also holds a slight edge in aggregate standing, with an average benchmark score of 8,558 compared to the GTX 675MX’s 8,427, placing it in the 44th percentile of all GPUs versus the NVIDIA card’s 43rd percentile. However, the comparison is complicated by the stark generational gap: the Arc A380 is a 2022 Alchemist part built on a 6 nm process, while the GTX 675MX is a 2012 Kepler mobile chip on 28 nm, and the data shows the Intel card wins the only head-to-head test available.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The Intel Arc A380 leads with an average benchmark score of 8,558, while the NVIDIA GeForce GTX 675MX trails at 8,427. The difference is 131 points, roughly 1.6% in favor of the Intel card.

Q: How do the two compare in Geekbench OpenCL performance?

A: The Intel Arc A380 scores 38,224 in Geekbench OpenCL, which is 256.5% higher than the GTX 675MX’s score of 10,723. This is the only benchmark where both GPUs have recorded scores.

Q: What is the transistor count difference between the two chips?

A: The Arc A380’s DG2-128 chip contains 7,200 million transistors on a 157 mm² die, while the GTX 675MX’s GK104 chip has 3,540 million transistors on a 294 mm² die. The Intel chip packs roughly double the transistors into about half the die area.

Q: Which GPU has more memory and bandwidth?

A: The Intel Arc A380 has 6 GB of GDDR6 memory on a 96-bit bus, delivering 186.0 GB/s bandwidth. The NVIDIA GeForce GTX 675MX has 2 GB of GDDR5 memory on a 256-bit bus, delivering 115.2 GB/s bandwidth.

Q: What are the power consumption figures for each card?

A: The Intel Arc A380 has a TDP of 75 W, while the NVIDIA GeForce GTX 675MX has a TDP of 100 W. The Intel card also lists a suggested PSU of 250 W, whereas the NVIDIA card has no suggested PSU figure.

Q: Which GPU supports newer graphics APIs?

A: The Intel Arc A380 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The NVIDIA GeForce GTX 675MX supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175, indicating the Intel card has a more modern feature set.

The Verdict

The data points to a clear winner for anyone comparing raw performance: the Intel Arc A380 is the superior GPU. Its 256.5% lead in Geekbench OpenCL over the GTX 675MX is overwhelming, and its higher average benchmark score (8,558 vs 8,427) confirms the trend. The Arc A380 also offers more VRAM (6 GB vs 2 GB), higher memory bandwidth (186.0 GB/s vs 115.2 GB/s), and more shading units (1,024 vs 960), all of which contribute to its decisive advantage.

However, the verdict is not purely about numbers. The GTX 675MX is a legacy mobile part from 2012, designed for laptops with an MXM form factor and no dedicated power connectors. The Arc A380 is a desktop card requiring a 1x 8-pin power connector and a 250 W PSU. For a user with an older laptop that accepts an MXM-B module, the GTX 675MX might be the only practical upgrade path, despite its inferior performance. For anyone building or upgrading a desktop system, the Arc A380 is the only rational choice—it wins every measured metric, supports newer APIs, and consumes less power (75 W vs 100 W). The data does not show a single benchmark where the GTX 675MX wins, so the verdict is unambiguous: choose the Arc A380 for performance, choose the GTX 675MX only if the MXM form factor is a hard requirement.

Head-to-Head Benchmarks

The only direct comparison available is Geekbench OpenCL, and the result is lopsided. The Intel Arc A380 scores 38,224, while the NVIDIA GeForce GTX 675MX scores 10,723. That is a delta of 256.5%, meaning the Intel card is more than 3.5 times faster in this compute workload. This is not a marginal victory—it is a generational leap. The Arc A380’s 4.198 TFLOPS of FP32 performance dwarfs the GTX 675MX’s 1,255.7 GFLOPS, which explains the massive gap. The Intel card also has a much higher pixel rate (65.60 GPixel/s vs 13.08 GPixel/s) and texture rate (131.2 GTexel/s vs 52.32 GTexel/s), though these figures are not directly benchmarked in the head-to-head data.

The aggregate benchmark scores tell a similar story, albeit less dramatically. The Arc A380’s average score of 8,558 places it just ahead of the GTX 675MX’s 8,427. The Intel card’s nearest rival is the AMD FirePro W5170M (8,595, -0.4%), while the NVIDIA card’s nearest rival is the AMD Radeon 880M (8,436, -0.1%). This suggests both GPUs sit in the same performance tier when averaged across all tests, but the Geekbench OpenCL result indicates the Arc A380 has a significant edge in compute-heavy tasks. The GTX 675MX has no recorded wins in any head-to-head benchmark, reinforcing the conclusion that the Intel card is strictly superior in every measured test.

Specification Differences

The two GPUs differ in nearly every fundamental specification. The Intel Arc A380 uses a 6 nm process, while the GTX 675MX uses 28 nm—a massive fabrication gap. The Arc A380’s chip, DG2-128, has 7,200 million transistors on a 157 mm² die, giving a transistor density of 45.9M per mm². The GTX 675MX’s GK104 chip has 3,540 million transistors on a 294 mm² die, with a density of just 12.0M per mm². The Intel chip is smaller, denser, and has over twice as many transistors.

Memory configurations diverge sharply. The Arc A380 has 6 GB of GDDR6 on a 96-bit bus, providing 186.0 GB/s of bandwidth. The GTX 675MX has 2 GB of GDDR5 on a 256-bit bus, providing 115.2 GB/s. Despite the wider bus, the older memory type and lower clock speed (900 MHz vs 1937 MHz) result in lower bandwidth. The Intel card also has more shading units (1,024 vs 960) and the same number of ROPs (32), but fewer TMUs (64 vs 80). The Arc A380 includes 8 ray tracing cores, which the GTX 675MX lacks entirely.

Power and physical requirements differ as well. The Arc A380 has a 75 W TDP and requires a 1x 8-pin power connector, while the GTX 675MX has a 100 W TDP and no power connectors, relying on the MXM slot. The Intel card is a dual-slot design measuring 222 mm in length, while the NVIDIA card is an MXM module with no listed dimensions. The Arc A380 uses PCIe 4.0 x8, while the GTX 675MX uses MXM-B (3.0). Display outputs also differ: the Arc A380 has 1x HDMI 2.1 and 3x DisplayPort 2.0, whereas the GTX 675MX’s outputs are listed as "Portable Device Dependent."

Architecture Differences

The architectural divide between these two GPUs is vast. The Intel Arc A380 is built on the Xe-HPG architecture, part of the Alchemist generation (Arc 3), fabricated on a 6 nm TSMC process. It uses the DG2-128 chip, which features 1,024 shading units, 64 TMUs, 32 ROPs, and 8 dedicated ray tracing cores. The architecture supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, indicating full support for hardware ray tracing and mesh shaders. The FP32 throughput is 4.198 TFLOPS, with FP16 at 8.397 TFLOPS (2:1 ratio).

The NVIDIA GeForce GTX 675MX is based on the Kepler architecture, from the GeForce 600M generation, fabricated on a 28 nm TSMC process. It uses the GK104 chip, which has 960 shading units, 80 TMUs, and 32 ROPs. There are no ray tracing cores or tensor cores. The FP32 throughput is 1,255.7 GFLOPS (1.256 TFLOPS), and FP16 performance is not listed. The architecture supports DirectX 12 (11_0) and Vulkan 1.2.175, which is older and lacks the features of DirectX 12 Ultimate. The Kepler design is a decade old, and the data shows it cannot match the modern Xe-HPG architecture in compute performance, as evidenced by the 256.5% deficit in Geekbench OpenCL.

Where Each One Wins

The Intel Arc A380 wins in every measurable category. It has a higher average benchmark score (8,558 vs 8,427), a higher percentile ranking (44th vs 43rd), and the only head-to-head win (Geekbench OpenCL: 38,224 vs 10,723). It offers more memory (6 GB vs 2 GB), higher bandwidth (186.0 GB/s vs 115.2 GB/s), more shading units (1,024 vs 960), and ray tracing support. It also draws less power (75 W vs 100 W), making it more efficient for the performance delivered. For desktop users, the Arc A380 is the clear choice for modern gaming, compute workloads, and any application that leverages DirectX 12 Ultimate features.

The NVIDIA GeForce GTX 675MX’s only advantage lies in its form factor and legacy compatibility. As an MXM module, it can be installed in laptops designed for MXM-B slots, which the desktop-bound Arc A380 cannot. The GTX 675MX also has a wider memory bus (256-bit vs 96-bit), which in theory could favor bandwidth-sensitive tasks, but the data shows its actual bandwidth is lower (115.2 GB/s vs 186.0 GB/s). It has more TMUs (80 vs 64) and no power connector requirement, simplifying installation in portable systems. The GTX 675MX is also from 2012, meaning it is compatible with older software environments that may lack drivers for newer Intel GPUs. However, in pure performance, the data shows no scenario where the GTX 675MX wins. The Arc A380 is the superior part for anyone who can accommodate a dual-slot PCIe card.