NVIDIA GeForce GTX 780 vs NVIDIA GeForce RTX 3080 Comparison

Head-to-Head Benchmarks

The recorded data contains two direct benchmark comparisons between the NVIDIA GeForce RTX 3080 and the NVIDIA GeForce GTX 780, and in both instances the RTX 3080 emerges as the clear winner. The most dramatic result comes from the Geekbench OpenCL test, where the RTX 3080 scores 152,423 against the GTX 780's 22,863. That represents a 566.7% advantage, meaning the newer card delivers roughly six and a half times the compute throughput in this particular workload. The margin is so large that the GTX 780's score appears almost as a rounding error in comparison.

The second head-to-head test, Geekbench Vulkan, shows a narrower but still decisive gap. The RTX 3080 posts 33,620 points, while the GTX 780 manages 24,514, putting the RTX 3080 ahead by 37.1%. This smaller margin reflects the fact that Vulkan is a lower-level API that can extract more efficiency from older hardware, yet the RTX 3080 still holds a comfortable lead. The benchmark summary records two wins for the RTX 3080 and zero wins for the GTX 780, so the head-to-head outcome is unambiguous.

Looking at the broader database context, the RTX 3080's average benchmark score of 23,172 places it in the 68th percentile of all GPUs tracked. Its nearest rivals in the database are the NVIDIA P106-100 at 23,249 (0.3% behind), the AMD Radeon Pro Vega 16 at 23,250 (0.3% behind), the AMD Radeon RX 6600M at 23,273 (0.4% behind), and the AMD Radeon R9 M290X at 23,276 (0.4% behind). These deltas are tiny, indicating that the RTX 3080 sits in a dense cluster of similarly performing cards in the overall rankings.

The GTX 780, by contrast, has an average benchmark score of 19,164 and sits in the 64th percentile. Its nearest rivals are the NVIDIA TITAN Xp at 19,177 (0.1% behind), the NVIDIA Tesla K20m at 19,089 (0.4% ahead), the NVIDIA GeForce RTX 4050 Mobile at 19,049 (0.6% ahead), and the AMD Radeon RX 6600 at 19,036 (0.7% ahead). The GTX 780 is thus positioned just below the RTX 3080 in percentile terms, though the raw average score difference of 4,008 points (roughly 21%) shows a meaningful performance separation.

Architecture Differences

The two cards come from entirely different generations and manufacturing eras. The RTX 3080 is built on the Ampere architecture using the GA102 chip, fabricated on Samsung's 8 nm process. It packs 28,300 million transistors into a 628 mm² die, yielding a transistor density of 45.1 million per square millimeter. The GTX 780, on the other hand, uses the Kepler architecture with the GK110 chip, manufactured by TSMC on a 28 nm process. It contains 7,080 million transistors on a 561 mm² die, giving a density of just 12.6 million per square millimeter. The RTX 3080 therefore crams over four times as many transistors into a slightly larger die, a direct consequence of the much finer manufacturing node.

Memory configurations diverge sharply as well. The RTX 3080 ships with 10 GB of GDDR6X memory running at 19 Gbps effective across a 320-bit bus, producing 760.3 GB/s of bandwidth. The GTX 780 offers 3 GB of GDDR5 at 6 Gbps effective on a 384-bit bus, yielding 288.4 GB/s. Despite the GTX 780's wider memory bus, the RTX 3080 still delivers more than two and a half times the bandwidth, thanks to the far faster memory technology.

Compute resources also favor the newer card overwhelmingly. The RTX 3080 has 8,704 shading units, 272 texture mapping units, and 96 raster operations pipelines. It also includes 68 dedicated ray tracing cores and 272 tensor cores, features the GTX 780 lacks entirely. The GTX 780 has 2,304 shading units, 192 TMUs, and 48 ROPs, so the RTX 3080 offers roughly 3.8 times the shading units, 1.4 times the TMUs, and double the ROPs. The pixel rate for the RTX 3080 is 164.2 GPixel/s versus 43.30 GPixel/s for the GTX 780, and the texture rate is 465.1 GTexel/s versus 173.2 GTexel/s. Floating point performance tells a similar story: the RTX 3080 delivers 29.77 TFLOPS in FP32, while the GTX 780 manages 4.156 TFLOPS, a factor of over seven. The RTX 3080 also supports FP16 at 29.77 TFLOPS, a capability the GTX 780 does not list.

Power and connectivity differ as well. The RTX 3080 has a 320 W TDP with a suggested 700 W power supply and a single 12-pin connector. The GTX 780 draws 250 W with a suggested 600 W PSU and uses one 6-pin plus one 8-pin connector. Both are dual-slot cards, but the RTX 3080 is slightly longer at 285 mm versus 267 mm, with near-identical height and width. The RTX 3080 uses a PCIe 4.0 x16 interface, while the GTX 780 uses PCIe 3.0 x16. Display outputs also differ: the RTX 3080 offers one HDMI 2.1 and three DisplayPort 1.4a outputs, whereas the GTX 780 has two DVI, one HDMI 1.4a, and one DisplayPort 1.2. The RTX 3080 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4; the GTX 780 supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175.

FAQ

Q: Which card wins in OpenCL compute performance?

A: The RTX 3080 scores 152,423 in Geekbench OpenCL, a 566.7% advantage over the GTX 780's 22,863.

Q: Is the GTX 780 competitive in Vulkan workloads?

A: The GTX 780 trails by 37.1% in Geekbench Vulkan, scoring 24,514 versus the RTX 3080's 33,620, so it is not competitive but the gap is far smaller than in OpenCL.

Q: How do their average benchmark scores compare?

A: The RTX 3080 averages 23,172 across all recorded benchmarks, while the GTX 780 averages 19,164, a difference of about 21% in favor of the RTX 3080.

Q: What are the key memory differences?

A: The RTX 3080 has 10 GB of GDDR6X with 760.3 GB/s bandwidth on a 320-bit bus, while the GTX 780 has 3 GB of GDDR5 with 288.4 GB/s on a 384-bit bus.

Q: Does the GTX 780 support ray tracing?

A: No, the GTX 780 has no ray tracing cores, whereas the RTX 3080 includes 68 dedicated RT cores.

Q: How do the process nodes compare?

A: The RTX 3080 uses Samsung's 8 nm process with 28,300 million transistors, while the GTX 780 uses TSMC's 28 nm process with 7,080 million transistors.

The Verdict

The data points to a decisive recommendation for the RTX 3080 in almost every measurable category. Its 566.7% lead in OpenCL and 37.1% lead in Vulkan are backed by a 21% advantage in average benchmark score and a higher percentile ranking (68th versus 64th). The architecture gap is generational: the RTX 3080 brings ray tracing, tensor cores, a modern 8 nm process, and over seven times the FP32 throughput. The GTX 780 retains only a narrower memory bus (384-bit versus 320-bit) and a lower power draw (250 W versus 320 W), but those advantages do not translate into competitive performance. For any workload involving modern APIs, compute, or ray tracing, the RTX 3080 is the clear choice. The GTX 780 remains a functional card for older DirectX 11 titles or Vulkan applications where its 37.1% deficit may still be acceptable, but the benchmark results show it is outclassed by a wide margin.

Specification Differences

| Specification | NVIDIA GeForce RTX 3080 | NVIDIA GeForce GTX 780 |

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

| Chip | GA102 | GK110 |

| Architecture | Ampere | Kepler |

| Process Node | 8 nm | 28 nm |

| Foundry | Samsung | TSMC |

| Transistors | 28,300 million | 7,080 million |

| Die Size | 628 mm² | 561 mm² |

| Transistor Density | 45.1M / mm² | 12.6M / mm² |

| Base Clock | 1440 MHz | 863 MHz |

| Boost Clock | 1710 MHz | 902 MHz |

| Memory Clock | 19 Gbps effective | 6 Gbps effective |

| Memory Size | 10 GB | 3 GB |

| Memory Type | GDDR6X | GDDR5 |

| Memory Bus Width | 320 bit | 384 bit |

| Memory Bandwidth | 760.3 GB/s | 288.4 GB/s |

| Shading Units | 8704 | 2304 |

| TMUs | 272 | 192 |

| ROPs | 96 | 48 |

| RT Cores | 68 | None |

| Tensor Cores | 272 | None |

| Pixel Rate | 164.2 GPixel/s | 43.30 GPixel/s |

| Texture Rate | 465.1 GTexel/s | 173.2 GTexel/s |

| FP32 Performance | 29.77 TFLOPS | 4.156 TFLOPS |

| FP16 Performance | 29.77 TFLOPS (1:1) | None |

| TDP | 320 W | 250 W |

| Power Connectors | 1x 12-pin | 1x 6-pin + 1x 8-pin |

| Suggested PSU | 700 W | 600 W |

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

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

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

| Vulkan Support | 1.4 | 1.2.175 |

| Length | 285 mm | 267 mm |

| Height | 112 mm | 111 mm |

| Width | 40 mm | 38 mm |

| Release Date | 2020-08-31 | 2013-05-22 |

| Launch MSRP | 699 USD | 649 USD |