NVIDIA GeForce GTX 780 vs NVIDIA GeForce RTX 5060 Mobile Comparison

Head-to-Head Benchmarks

The recorded data shows a decisive performance shift between these two generations. In the two shared benchmark tests, the NVIDIA GeForce RTX 5060 Mobile wins both, and the margins are enormous.

The first comparison, Geekbench OpenCL, shows the RTX 5060 Mobile scoring 96,969 points against the GTX 780's 22,863 points. That is a delta of 324.1% in favor of the newer part. To put that in context, the RTX 5060 Mobile delivers more than four times the raw compute throughput in this test. The GTX 780 was a flagship desktop card in its day, but the OpenCL result suggests that architectural advances plus a much newer process node have completely overturned the generational hierarchy.

The second shared test, Geekbench Vulkan, tells a similar story. The RTX 5060 Mobile scores 96,451, while the GTX 780 manages 24,514. The delta here is 293.5%. Vulkan is a modern low-level API, and the GTX 780's Kepler architecture was never designed with it in mind. Its Vulkan support is limited to version 1.2.175, whereas the RTX 5060 Mobile supports Vulkan 1.4. The performance gap in this test likely reflects both hardware capabilities and driver maturity for modern APIs.

It is notably the benchmark database only records two head-to-head tests between these cards. The RTX 5060 Mobile wins both, giving it a 2-0 record. The GTX 780 has no wins in the shared suite. However, the GTX 780 does have one additional benchmark result in the database: Geekbench Metal, where it scores 10,114. The RTX 5060 Mobile has no Metal result recorded, so that test cannot be compared directly.

Looking at average benchmark scores across all recorded tests, the RTX 5060 Mobile averages 22,435 points, while the GTX 780 averages 19,164 points. That is a 17% advantage for the mobile part overall, though the head-to-head deltas are far larger because the shared tests heavily favor the newer architecture.

Architecture Differences

The architectural gap between these two GPUs is vast, spanning over a decade of development. The RTX 5060 Mobile uses the GB206 chip built on Blackwell 2.0 architecture, manufactured on a 5 nm process at TSMC. The GTX 780 uses the GK110 chip on Kepler architecture, built on a 28 nm process, also at TSMC. The process node difference alone, 5 nm versus 28 nm, explains much of the efficiency and density disparity.

Transistor counts tell a striking story. The RTX 5060 Mobile packs 21,900 million transistors onto a die of 181 mm². The GTX 780 has 7,080 million transistors spread across a much larger 561 mm² die. That means the RTX 5060 Mobile achieves a transistor density of 121.0 million per mm², while the GTX 780 manages only 12.6 million per mm². The newer chip fits roughly three times the transistors onto one-third the silicon area.

Memory configurations differ substantially as well. The RTX 5060 Mobile carries 8 GB of GDDR7 memory on a 128 bit bus, delivering 384.0 GB/s of bandwidth. The GTX 780 has 3 GB of GDDR5 on a much wider 384 bit bus, yielding 288.4 GB/s. Despite having three times the bus width, the older card cannot match the bandwidth of the newer one because GDDR7's effective data rate is so much higher. The RTX 5060 Mobile runs its memory at 1500 MHz with 24 Gbps effective speed, while the GTX 780 runs at 1502 MHz with 6 Gbps effective.

Compute resources have been rebalanced. The RTX 5060 Mobile has 3,328 shading units, 104 TMUs, and 48 ROPs. The GTX 780 has 2,304 shading units, 192 TMUs, and 48 ROPs. Interestingly, the older card has nearly double the texture units, which gives it a higher texture rate of 173.2 GTexel/s compared to the RTX 5060 Mobile's 151.3 GTexel/s. However, the newer card's pixel rate of 69.84 GPixel/s far exceeds the GTX 780's 43.30 GPixel/s.

The RTX 5060 Mobile also introduces hardware that simply did not exist in the Kepler era: 26 ray tracing cores and 104 tensor cores. The GTX 780 has neither, as ray tracing and tensor acceleration were not part of GPU design in 2013. This is a fundamental capability difference, not just a performance difference.

Power requirements are dramatically different. The RTX 5060 Mobile is rated at 45 W TDP and uses no external power connectors, fitting an IGP form factor. The GTX 780 draws 250 W, requires a dual-slot cooler, and needs both a 6-pin and an 8-pin power connector. The database also lists a suggested PSU of 600 W for the GTX 780, while no PSU recommendation is given for the mobile part.

The bus interface has advanced from PCIe 3.0 x16 to PCIe 5.0 x16. The GTX 780's display outputs include 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2, while the RTX 5060 Mobile's outputs are listed as portable device dependent, reflecting its laptop-oriented design.

Where Each One Wins

The RTX 5060 Mobile wins in every shared benchmark, and the reasons are clear from the architecture data. Its strengths lie in modern API performance, raw compute density, and memory bandwidth efficiency. The Geekbench OpenCL score of 96,969 shows a 324.1% advantage over the GTX 780, and the Vulkan score of 96,451 demonstrates a 293.5% lead. For anyone running current games or compute workloads that leverage DirectX 12 Ultimate, Vulkan 1.4, or ray tracing, the RTX 5060 Mobile is the only viable option of the two.

The GTX 780 does retain a few technical advantages, even if they do not translate into benchmark wins. Its texture rate of 173.2 GTexel/s is higher than the RTX 5060 Mobile's 151.3 GTexel/s, which could theoretically benefit certain texture-bound workloads. Its 384 bit memory bus is three times wider, even though the newer memory technology makes that width less important. And its 192 TMUs versus 104 could matter in legacy applications that are heavily texture-cached. The GTX 780 also has a Metal benchmark score of 10,114, which is a capability the RTX 5060 Mobile does not have recorded.

For gaming workloads on modern APIs, the choice is clear. The RTX 5060 Mobile supports DirectX 12 Ultimate (12_2), while the GTX 780 only reaches DirectX 12 (11_0). That feature-level gap means newer games with mesh shaders, variable rate shading, or ray tracing will not run properly on the GTX 780 at all. The RTX 5060 Mobile's ray tracing cores and tensor cores open up entire categories of rendering and AI workloads that the Kepler card cannot touch.

For power-constrained environments, the RTX 5060 Mobile is also the obvious winner. Its 45 W TDP versus 250 W means it can operate in laptops and compact systems without the dual-slot cooler, dual-connector, and 600 W PSU requirements of the GTX 780. The GTX 780 is end-of-life production status, while the RTX 5060 Mobile is active and was released on 2025-05-19.

FAQ

Q: Which GPU has higher memory bandwidth?

A: The NVIDIA GeForce RTX 5060 Mobile as well as 384.0 GB/s, while the GTX 780 has 288.4 GB/s.

Q: Does the GTX 780 support ray tracing?

A: The GTX 780 has no ray tracing cores in the database. The RTX 5060 Mobile has 26 ray tracing cores.

Q: What is the TDP difference between the two cards?

A: The RTX 5060 Mobile has a 45 W TDP. The GTX 780 is rated at 250 W.

Q: Which GPU is an active production card?

A: The RTX 780 Mobile has Active production status. The GTX 780 is end-of-life with a release date of 2025-05-19.

Q: What is the GTX 780's launch MSRP?

A: The GTX 780 has a launch MSRP of 649 USD.

The Verdict

The data points to a single conclusion: the RTX 5060 Mobile is the superior GPU in every measurable shared benchmark. Its 324.1% OpenCL advantage and 293.5% Vulkan advantage are not incremental improvements; they are generational leaps. The architectural differences support these results. A 5 nm process with 21,900 million transistors, GDDR7 memory, ray tracing cores, and tensor cores simply outclasses a 28 nm Kepler chip from 2013.

Who should pick the RTX 5060 Mobile: anyone who needs modern API support, ray tracing, AI acceleration, high memory bandwidth, or low power consumption. It is the only choice for current gaming, and its 67th percentile ranking among all GPUs places it comfortably ahead of the GTX 780's 64th percentile.

Who should pick the GTX 780: essentially no one, based on the recorded data. Its only advantages are a higher texture rate of 173.2 GTexel/s and a wider 384 bit memory bus, neither of which translates into benchmark wins. It is end-of-life, draws 250 W, requires external power connectors, and lacks every modern hardware feature. The GTX 780's nearest rivals in the database include the RTX 4050 Mobile at a 0.6% delta, which shows it sits near modern entry-level mobile parts, not flagship desktop cards. The RTX 5060 Mobile's nearest rivals include the RTX 4060 Mobile at a 1.3% delta, placing it in a much higher performance tier.

Specification Differences

| Specification | NVIDIA GeForce RTX 5060 Mobile | NVIDIA GeForce GTX 780 |

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

| Architecture | Blackwell 2.0 | Kepler |

| Process Node | 5 nm | 28 nm |

| Transistors | 21,900 million | 7,080 million |

| Die Size | 181 mm² | 561 mm² |

| Transistor Density | 121.0M / mm² | 12.6M / mm² |

| Base Clock | 952 MHz | 863 MHz |

| Boost Clock | 1455 MHz | 902 MHz |

| Memory Size | 8 GB | 3 GB |

| Memory Type | GDDR7 | GDDR5 |

| Bus Width | 128 bit | 384 bit |

| Bandwidth | 384.0 GB/s | 288.4 GB/s |

| Shading Units | 3328 | 2304 |

| TMUs | 104 | 192 |

| ROPs | 48 | 48 |

| RT Cores | 26 | None |

| Tensor Cores | 104 | None |

| Pixel Rate | 69.84 GPixel/s | 43.30 GPixel/s |

| Texture Rate | 151.3 GTexel/s | 173.2 GTexel/s |

| FP32 | 9.684 TFLOPS | 4.156 TFLOPS |

| FP16 | 9.684 TFLOPS (1:1) | None |

| TDP | 45 W | 250 W |

| Slot Width | IGP | Dual-slot |

| Power Connectors | None | 1x 6-pin + 1x 8-pin |

| Suggested PSU | None | 600 W |

| Bus Interface | PCIe 5.0 x16 | PCIe 3.0 x16 |

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

| Vulkan | 1.4 | 1.2.175 |

| Production Status | Active | End-of-life |

| Release Date | 2025-05-19 | 2013-05-22 |

| Predecessor | GeForce 40 Mobile | GeForce 600 |

| Successor | None | GeForce 900 |