NVIDIA GeForce GTX 780M vs NVIDIA GeForce GTX 960 Comparison

The Verdict

The benchmark data splits cleanly by workload. The NVIDIA GeForce GTX 960 wins two of the three recorded head-to-head tests, taking Geekbench Metal and Geekbench OpenCL decisively. The NVIDIA GeForce GTX 780M wins the remaining test, Geekbench Vulkan, by a substantial margin. For users prioritizing OpenCL compute or Metal performance, the GTX 960 is the clear choice from the data. For Vulkan-based workloads, the GTX 780M holds a commanding lead.

The GTX 960 posts an average benchmark score of 9273, placing it at the 45th percentile of all GPUs in the database. The GTX 780M counters with an average score of 11261, placing it at the 50th percentile. Despite the GTX 780M's higher average, the GTX 960 wins the majority of direct comparisons. The GTX 780M sits within 0.3% of the AMD Radeon Pro WX 3200 and AMD FirePro W4300, while the GTX 960 trades blows with the NVIDIA GeForce GTX 465 (0.2% behind) and NVIDIA GeForce GTX 850M (0.3% behind). The GTX 960's nearest rival group is tightly clustered, with all deltas under 1%.

The GTX 780M's average score is 21.5% higher than the GTX 960's average, but that aggregate hides the per-test reality. The GTX 960 wins OpenCL by 48.2% and Metal by 5.5%, while the GTX 780M wins Vulkan by 37.5%. The verdict depends entirely on the API in question. For mixed workloads, the GTX 780M's higher average and percentile rank make it the safer all-around pick in the database's scoring system.

Architecture Differences

The two GPUs come from different NVIDIA architectures and generations. The GTX 780M uses the GK104 chip on the Kepler architecture, belonging to the GeForce 700M mobile generation. The GTX 960 uses the GM206 chip on the Maxwell 2.0 architecture, belonging to the GeForce 900 desktop generation. Both are fabricated by TSMC on a 28 nm process, but the transistor counts and die sizes differ notably.

The GTX 780M packs 3,540 million transistors on a 294 mm² die, yielding a transistor density of 12.0M per mm². The GTX 960 contains 2,940 million transistors on a 228 mm² die, achieving a higher density of 12.9M per mm². The GTX 780M has more raw hardware: 1536 shading units, 128 texture mapping units, and 32 ROPs. The GTX 960 scales down to 1024 shading units and 64 TMUs, while keeping 32 ROPs. Despite fewer cores, the GTX 960 runs at higher clocks, with a base of 1127 MHz and boost of 1178 MHz compared to the GTX 780M's 771 MHz base and 797 MHz boost.

Memory configurations also diverge. The GTX 780M offers 4 GB of GDDR5 on a 256-bit bus, delivering 160.0 GB/s of bandwidth. The GTX 960 provides 2 GB of GDDR5 on a 128-bit bus, with 112.2 GB/s of bandwidth. The GTX 960's memory runs at 1753 MHz (7 Gbps effective) versus the GTX 780M's 1250 MHz (5 Gbps effective). The GTX 780M's wider bus compensates for the lower clock, resulting in higher overall bandwidth.

Feature support differs in API levels. The GTX 780M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The GTX 960 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The GTX 960's higher DirectX feature level and newer Vulkan version reflect its later release. Physical form factors also differ: the GTX 780M is an MXM module with no power connectors, while the GTX 960 is a dual-slot card with a 1x 6-pin connector and a suggested PSU of 300 W. The GTX 960 measures 241 mm (9.5 inches) in length. The GTX 780M's display outputs are portable-device dependent, while the GTX 960 offers 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.2.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 780M, with an average benchmark score of 11261 compared to the GTX 960's 9273. The GTX 780M also ranks higher at the 50th percentile versus the GTX 960's 45th percentile.

Q: How large is the GTX 960's OpenCL advantage?

A: The GTX 960 scores 18925 in Geekbench OpenCL versus the GTX 780M's 12769, a 32.5% lead. This is the largest margin in any head-to-head test between the two.

Q: Does the GTX 780M win any benchmark?

A: Yes, the GTX 780M wins Geekbench Vulkan with a score of 12696 against the GTX 960's 9231, a 37.5% advantage. This is the only head-to-head test the GTX 780M wins.

Q: What are the memory differences?

A: The GTX 780M has 4 GB of GDDR5 on a 256-bit bus with 160.0 GB/s bandwidth. The GTX 960 has 2 GB of GDDR5 on a 128-bit bus with 112.2 GB/s bandwidth. The GTX 960's memory runs at 7 Gbps effective versus 5 Gbps effective on the GTX 780M.

Q: Which GPU has more shading units?

A: The GTX 780M has 1536 shading units, while the GTX 960 has 1024. The GTX 780M also has 128 TMUs versus 64 on the GTX 960, though both have 32 ROPs.

Q: How do their pixel and texture rates compare?

A: The GTX 960 achieves a higher pixel rate at 37.70 GPixel/s versus 25.50 GPixel/s on the GTX 780M. The GTX 780M has the higher texture rate at 102.0 GTexel/s versus 75.39 GTexel/s on the GTX 960.

Specification Differences

| Specification | GTX 780M | GTX 960 |

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

| Chip | GK104 | GM206 |

| Architecture | Kepler | Maxwell 2.0 |

| Generation | GeForce 700M | GeForce 900 |

| Transistors | 3,540 million | 2,940 million |

| Die Size | 294 mm² | 228 mm² |

| Transistor Density | 12.0M / mm² | 12.9M / mm² |

| Base Clock | 771 MHz | 1127 MHz |

| Boost Clock | 797 MHz | 1178 MHz |

| Memory Clock | 1250 MHz, 5 Gbps effective | 1753 MHz, 7 Gbps effective |

| Memory Size | 4 GB | 2 GB |

| Memory Bus Width | 256 bit | 128 bit |

| Memory Bandwidth | 160.0 GB/s | 112.2 GB/s |

| Shading Units | 1536 | 1024 |

| TMUs | 128 | 64 |

| Pixel Rate | 25.50 GPixel/s | 37.70 GPixel/s |

| Texture Rate | 102.0 GTexel/s | 75.39 GTexel/s |

| FP32 | 2.448 TFLOPS | 2.413 TFLOPS |

| TDP | 122 W | 120 W |

| Slot Width | MXM Module | Dual-slot |

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

| Suggested PSU | Not recorded | 300 W |

| Bus Interface | MXM-B (3.0) | PCIe 3.0 x16 |

| Display Outputs | Portable Device Dependent | 1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.2 |

| DirectX | 12 (11_0) | 12 (12_1) |

| Vulkan | 1.2.175 | 1.4 |

| Release Date | 2013-05-10 | 2015-01-21 |

| Predecessor | GeForce 600M | GeForce 700 |

| Successor | GeForce 800M | GeForce 10 |

| Launch MSRP | Not recorded | 199 USD |

Head-to-Head Benchmarks

The Geekbench OpenCL test delivers the most lopsided result. The GTX 960 scores 18925 against the GTX 780M's 12769, a 32.5% margin. This aligns with the GTX 960's higher boost clock of 1178 MHz versus 797 MHz, despite having fewer shading units. The GTX 960's newer Maxwell 2.0 architecture appears to extract more compute throughput per shader in this workload.

Geekbench Metal shows a narrower win for the GTX 960. The GTX 960 scores 8773 versus 8319 on the GTX 780M, a 5.2% difference. Both GPUs support OpenGL 4.6, but the GTX 960's DirectX 12 (12_1) feature level and newer Vulkan 1.4 support suggest a more modern API stack. The Metal result is close enough that real-world differences would be modest.

Geekbench Vulkan flips the script. The GTX 780M scores 12696 against 9231 on the GTX 960, a 37.5% victory. This is surprising given the GTX 960's newer Vulkan 1.4 support versus 1.2.175 on the GTX 780M. The GTX 780M's larger memory bus (256 bit vs 128 bit) and higher bandwidth (160.0 GB/s vs 112.2 GB/s) may contribute to this Vulkan advantage, as memory-bound workloads can favor wider buses.

The FP32 compute figures are nearly identical: 2.448 TFLOPS for the GTX 780M and 2.413 TFLOPS for the GTX 960. Yet the benchmark results diverge sharply by API. This suggests architectural efficiency differences rather than raw throughput explain the outcome. The GTX 780M's 1536 shading units at lower clocks versus the GTX 960's 1024 shading units at higher clocks produce different performance profiles depending on the workload characteristics.

Where Each One Wins

The GTX 960 wins in OpenCL compute and Metal workloads based on the recorded data. Its 32.5% OpenCL lead and 5.2% Metal lead make it the preferred choice for applications leveraging those APIs. The GTX 960 also offers a higher pixel rate (37.70 GPixel/s vs 25.50 GPixel/s), which benefits rasterization-heavy tasks. Its 300 W suggested PSU and dual-slot form factor indicate a desktop-oriented design with standard display outputs including HDMI 2.0 and three DisplayPort 1.2 connections.

The GTX 780M wins decisively in Vulkan, with a 37.5% advantage. Its 4 GB memory capacity and 256-bit bus provide double the bus width and 42.7% more bandwidth than the GTX 960. For Vulkan-based games or compute workloads that stress memory bandwidth, the GTX 780M's specifications align with its benchmark victory. The GTX 780M also has a higher texture rate at 102.0 GTexel/s versus 75.39 GTexel/s, aided by its 128 TMUs.

The GTX 780M's higher average benchmark score (11261 vs 9273) and better percentile rank (50th vs 45th) suggest broader overall competency across the database's test suite. However, the GTX 960 wins more direct head-to-head tests, taking two of three. Users should match the GPU to their primary API. OpenCL and Metal users should choose the GTX 960. Vulkan users should choose the GTX 780M. The GTX 780M's MXM form factor suits portable devices, while the GTX 960's PCIe 3.0 x16 interface and 241 mm length suit desktop builds. Both are end-of-life products, but the GTX 960 carries a launch MSRP of 199 USD, while the GTX 780M has no recorded launch MSRP.