Intel Arc A380 vs NVIDIA GeForce GTX 760 Comparison

Head-to-Head Benchmarks

The recorded data shows a decisive victory for the Intel Arc A380 in the two directly comparable benchmark tests. In the Geekbench OpenCL test, the Intel Arc A380 scores 38,224 against the NVIDIA GeForce GTX 760’s 11,299, a margin of 70.4% in favor of the Intel part. This is not a marginal difference; it represents a generational leap in raw compute throughput, as OpenCL exercises general-purpose GPU compute rather than just rasterization.

The Geekbench Vulkan test tells a similar story. The Intel Arc A380 posts 36,736 points, while the NVIDIA GeForce GTX 760 manages 12,551. The delta here is 65.8% in favor of Intel. Vulkan is a low-level graphics API that stresses driver overhead and modern hardware features, both of which favor the much younger Intel architecture. The NVIDIA card was released in 2013, and its Kepler architecture lacks the modern scheduling and asynchronous compute capabilities that the Xe-HPG design from Intel brings to the table.

Looking at the broader average benchmark scores, the picture is more nuanced than the head-to-head results alone suggest. The NVIDIA GeForce GTX 760 has an average benchmark score of 9,458 across all recorded tests, while the Intel Arc A380 averages 8,558. That puts the NVIDIA card 10.5% ahead on aggregate, despite losing both direct comparisons. This discrepancy indicates that the GTX 760 performs relatively better in certain legacy or driver-optimized workloads, while the Arc A380 excels in compute-heavy and modern API scenarios.

The percentile rankings reinforce this split. The GTX 760 sits at the 46th percentile of all GPUs in the database, while the Arc A380 sits at the 44th percentile. These are adjacent rankings, meaning that in the full database context, neither card is dramatically superior to the other. The average score difference of 900 points (9,458 versus 8,558) is within the range of what one would expect from cards in the same performance tier, despite their vastly different ages and architectures.

Architecture Differences

The architectural gap between these two GPUs is enormous, reflecting nearly a decade of semiconductor progress. The NVIDIA GeForce GTX 760 uses the GK104 chip on a 28 nm process from TSMC, packing 3,540 million transistors into a 294 mm² die. That works out to a transistor density of 12.0 million per square millimeter. The Intel Arc A380 uses the DG2-128 chip on a 6 nm process, also from TSMC, with 7,200 million transistors in a much smaller 157 mm² die. Its density is 45.9 million transistors per square millimeter, nearly four times higher.

The core configurations differ in ways that reflect their respective design philosophies. The GTX 760 has 1,152 shading units, 96 texture mapping units, and 32 ROPs. The Arc A380 has 1,024 shading units, 64 TMUs, and 32 ROPs. The NVIDIA card has more shaders and TMUs, but the Intel card compensates with much higher clocks: 2000 MHz base and 2050 MHz boost against the GTX 760’s 980 MHz base and 1032 MHz boost. The clock advantage translates directly into compute throughput. The Arc A380 delivers 4.198 TFLOPS of FP32 performance, while the GTX 760 manages 2.378 TFLOPS. The Intel card is 76.5% ahead in raw FP32.

Memory subsystems also diverge sharply. The GTX 760 uses 2 GB of GDDR5 on a 256-bit bus, delivering 192.3 GB/s of bandwidth. The Arc A380 uses 6 GB of GDDR6 on a 96-bit bus, delivering 186.0 GB/s. The bandwidth figures are nearly identical, but the Intel card has three times the capacity. The NVIDIA card’s memory runs at an effective 6 Gbps, while the Intel card’s GDDR6 runs at an effective 15.5 Gbps. The narrower bus on the Intel card is compensated by the much faster memory clock.

The Intel Arc A380 includes 8 dedicated ray tracing cores, a feature entirely absent from the Kepler architecture. The GTX 760 predates hardware ray tracing by several generations. The Arc A380 also supports DirectX 12 Ultimate (12_2), while the GTX 760 is limited to DirectX 12 (11_0). Both cards support OpenGL 4.6, but the Intel card supports Vulkan 1.4 versus the NVIDIA card’s Vulkan 1.2.175.

Power consumption tells the story of process efficiency. The GTX 760 has a TDP of 170 W and requires a 450 W suggested power supply with dual 6-pin connectors. The Arc A380 has a TDP of 75 W and requires only a 250 W power supply with a single 8-pin connector. The Intel card delivers more than double the FP32 throughput while drawing less than half the power. The process node advantage, combined with the newer architecture, makes this an efficiency rout.

Display outputs also reflect the generational gap. The GTX 760 offers 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2. The Arc A380 offers 1x HDMI 2.1 and 3x DisplayPort 2.0. The Intel card supports modern display standards that the NVIDIA card cannot, including higher bandwidth for high refresh rate and high resolution monitors. The bus interface differs as well: the GTX 760 uses PCIe 3.0 x16, while the Arc A380 uses PCIe 4.0 x8, which provides comparable bandwidth on a newer standard.

The Verdict

The data points to a clear but conditional recommendation. For users running modern APIs and compute workloads, the Intel Arc A380 is the superior card. Its 70.4% lead in OpenCL and 65.8% lead in Vulkan demonstrate that it handles contemporary software far better than the aging Kepler design. The 6 GB memory capacity is triple that of the GTX 760, which matters for modern game textures and compute buffers. The ray tracing cores and DirectX 12 Ultimate support make it the only one of the two that can run current-generation graphics features.

However, the aggregate benchmark data shows the GTX 760 holding a slight edge in overall average score. At 9,458 versus 8,558, the NVIDIA card is 10.5% ahead across all recorded tests. This suggests that in certain legacy workloads, particularly those optimized for NVIDIA’s mature driver stack and older API paths, the GTX 760 still holds its own. The 46th percentile versus 44th percentile ranking indicates that both cards are in the same broad performance class.

The choice depends entirely on workload. For a modern gaming PC or compute workstation, the Arc A380 is the rational pick. For a system running older software that predates modern APIs, the GTX 760’s legacy performance and driver maturity may serve better. The power efficiency alone favors the Intel card in any always-on or thermally constrained scenario: 75 W versus 170 W TDP, with a 250 W versus 450 W suggested power supply. The GTX 760 is end-of-life with a 2013 release date, while the Arc A380, also end-of-life, was released in 2022. The older card has no path forward for modern features.

FAQ

Q: Which card has higher raw FP32 compute performance?

A: The Intel Arc A380 delivers 4.198 TFLOPS, which is 76.5% higher than the NVIDIA GeForce GTX 760’s 2.378 TFLOPS.

Q: How do the two cards compare in the Geekbench Vulkan test?

A: The Intel Arc A380 scores 36,736 against the GTX 760’s 12,551, a 65.8% advantage for the Intel card.

Q: Which card has more memory bandwidth?

A: The GTX 760 has 192.3 GB/s over a 256-bit bus, while the Arc A380 has 186.0 GB/s over a 96-bit bus. The NVIDIA card is 3.4% ahead in bandwidth, but the Intel card has 6 GB of capacity versus 2 GB.

Q: Does the Intel Arc A380 support ray tracing?

A: Yes, it has 8 dedicated ray tracing cores. The NVIDIA GeForce GTX 760 has no ray tracing cores at all.

Q: What is the power consumption difference?

A: The GTX 760 has a TDP of 170 W with a 450 W suggested PSU, while the Arc A380 has a TDP of 75 W with a 250 W suggested PSU. The Intel card draws 55.9% less power.

Q: Which card has a higher average benchmark score?

A: The NVIDIA GeForce GTX 760 averages 9,458 points across all recorded benchmarks, while the Intel Arc A380 averages 8,558 points, a 10.5% advantage for the NVIDIA card.

Where Each One Wins

The Intel Arc A380 wins decisively in modern compute workloads. Its OpenCL score of 38,224 is more than triple the GTX 760’s 11,299. The Vulkan result of 36,736 versus 12,551 shows the same pattern. These are the two tests where both cards have direct head-to-head data, and the Intel card wins both by overwhelming margins. The Arc A380 also wins on memory capacity with 6 GB versus 2 GB, on ray tracing capability with 8 dedicated cores, and on power efficiency with a 75 W TDP versus 170 W.

The NVIDIA GeForce GTX 760 wins in the aggregate benchmark average. Its 9,458 average score beats the Arc A380’s 8,558, despite losing both direct comparisons. This indicates that the GTX 760 performs relatively better in tests that are not part of the direct head-to-head set, likely including legacy DirectX paths and older OpenGL workloads. The GTX 760 also has a wider memory bus at 256 bits versus 96 bits, which can help in bandwidth-sensitive legacy workloads that do not benefit from the Arc’s higher clock speed.

For gaming with modern titles, the Arc A380’s DirectX 12 Ultimate support and ray tracing cores give it capabilities the GTX 760 simply cannot match. For esports and older games that rely on mature NVIDIA drivers, the GTX 760’s aggregate score advantage suggests it remains serviceable. The Arc A380’s PCIe 4.0 x8 interface is newer, but the GTX 760’s PCIe 3.0 x16 offers similar bandwidth for older platforms.

Specification Differences

| Specification | NVIDIA GeForce GTX 760 | Intel Arc A380 |

|---|---|---|

| Architecture | Kepler | Xe-HPG |

| Process Node | 28 nm | 6 nm |

| Transistors | 3,540 million | 7,200 million |

| Die Size | 294 mm² | 157 mm² |

| Transistor Density | 12.0M / mm² | 45.9M / mm² |

| Base Clock | 980 MHz | 2000 MHz |

| Boost Clock | 1032 MHz | 2050 MHz |

| Memory Size | 2 GB | 6 GB |

| Memory Type | GDDR5 | GDDR6 |

| Memory Bus | 256 bit | 96 bit |

| Memory Bandwidth | 192.3 GB/s | 186.0 GB/s |

| Shading Units | 1152 | 1024 |

| TMUs | 96 | 64 |

| ROPs | 32 | 32 |

| RT Cores | N/A | 8 |

| Pixel Rate | 24.77 GPixel/s | 65.60 GPixel/s |

| Texture Rate | 99.07 GTexel/s | 131.2 GTexel/s |

| FP32 | 2.378 TFLOPS | 4.198 TFLOPS |

| FP16 | N/A | 8.397 TFLOPS (2:1) |

| TDP | 170 W | 75 W |

| Power Connectors | 2x 6-pin | 1x 8-pin |

| Suggested PSU | 450 W | 250 W |

| Bus Interface | PCIe 3.0 x16 | PCIe 4.0 x8 |

| Display Outputs | 2x DVI, 1x HDMI 1.4a, 1x DisplayPort 1.2 | 1x HDMI 2.1, 3x DisplayPort 2.0 |

| DirectX | 12 (11_0) | 12 Ultimate (12_2) |

| Vulkan | 1.2.175 | 1.4 |

| Release Date | 2013-06-24 | 2022-06-13 |

| Launch MSRP | 249 USD | 149 USD |