NVIDIA GeForce GTX 760 vs NVIDIA GeForce GTX 960M Comparison

The NVIDIA GeForce GTX 960M and the NVIDIA GeForce GTX 760 are two end-of-life graphics cards from different eras, aimed at different segments. The GTX 960M is a mobile part built on the Maxwell architecture, while the GTX 760 is a desktop card from the Kepler generation. Despite their similar average benchmark scores, the data reveals a clear performance hierarchy, with the older desktop card holding a decisive advantage in raw compute and API-specific workloads. The following analysis breaks down their performance, specifications, and ideal use cases based solely on the provided benchmark data.

Head-to-Head Benchmarks

The head-to-head benchmark data shows a clean sweep for the GTX 760, though the margin of victory varies significantly depending on the test. In the Geekbench OpenCL test, the GTX 760 scores 11299 against the GTX 960M’s 11045. This gives the GTX 760 a 2.2% lead, a relatively narrow gap that suggests the two cards are in the same ballpark for general compute tasks. The GTX 960M’s Maxwell architecture appears to be efficient enough to keep it competitive in this workload, despite having fewer physical resources on paper.

The story changes dramatically in the Geekbench Vulkan test. Here, the GTX 760 scores 12551, while the GTX 960M manages only 8245. The deltaPct jumps to -34.3% in favor of the GTX 760, meaning the desktop card is roughly a third faster in this API. This is a massive difference and points to a fundamental advantage for the older card in modern, low-level graphics APIs. The Vulkan test often scales with raw shader throughput and memory bandwidth, both of which are areas where the GTX 760 has a substantial hardware lead. The GTX 960M’s score of 8245 is not just a minor deficit; it is a significant shortfall that would be noticeable in any Vulkan-based game or application.

The overall wins tally reinforces this result: the GTX 760 wins 2 benchmarks, while the GTX 960M wins 0. The average benchmark score for the GTX 960M is 9645, which is actually higher than the GTX 760’s average of 9458. This is a curious inversion. The GTX 960M’s average is buoyed by its OpenCL result and a Vulkan score that, while lower than the GTX 760’s, is still substantial. The GTX 760’s average is dragged down by its low Metal score of 4524, a test that the GTX 960M did not run. When looking at the shared tests, the GTX 760 is clearly ahead, but the inclusion of a Metal benchmark for the GTX 760 skews the overall averages. The practical takeaway is that in the two tests where both cards were measured, the GTX 760 is the superior performer, with the Vulkan result being the most decisive.

FAQ

Q: Which card has a higher average benchmark score?

A: The NVIDIA GeForce GTX 960M has a higher average benchmark score of 9645, compared to the GTX 760’s 9458. However, this average includes a Geekbench Metal score for the GTX 760, a test that the GTX 960M did not run.

Q: How does the GTX 760 perform in Vulkan compared to the GTX 960M?

A: The GTX 760 is significantly faster in Vulkan, scoring 12551 against the GTX 960M’s 8245. This represents a 34.3% advantage for the GTX 760, making it the clear winner in this API.

Q: Is the GTX 960M competitive with the GTX 760 in OpenCL?

A: Yes, the GTX 960M is close. It scores 11045 in OpenCL, trailing the GTX 760’s 11299 by only 2.2%. This is a minor difference and indicates comparable performance for general compute workloads.

Q: What is the memory configuration difference between the two cards?

A: The GTX 960M comes with 4 GB of GDDR5 memory on a 128-bit bus, providing 80.19 GB/s of bandwidth. The GTX 760 has 2 GB of GDDR5 memory on a 256-bit bus, offering 192.3 GB/s of bandwidth.

Q: Which card has a higher transistor count and die size?

A: The GTX 760 has a much larger chip. It uses 3,540 million transistors on a 294 mm² die, while the GTX 960M uses 1,870 million transistors on a 148 mm² die.

Q: What are the power requirements for each card?

A: The GTX 960M has a TDP of 75 W and uses no power connectors, drawing power from the motherboard via its MXM Module slot. The GTX 760 has a TDP of 170 W and requires two 6-pin power connectors, with a suggested PSU of 450 W.

Where Each One Wins

The GTX 760 is the outright winner for anyone prioritizing raw graphics performance, particularly in modern APIs. Its Vulkan score of 12551 is the highest single benchmark result in this comparison, making it the better choice for Vulkan-based games or applications. The 34.3% lead over the GTX 960M in this test is substantial and cannot be ignored. The GTX 760 also edges out the GTX 960M in OpenCL, albeit by a slim 2.2% margin, so it is also the safer bet for general-purpose compute tasks. With a texture rate of 99.07 GTexel/s and a pixel rate of 24.77 GPixel/s, the GTX 760 has the throughput to handle higher resolutions and more demanding graphical effects. Its 256-bit memory bus provides 192.3 GB/s of bandwidth, which is more than double the GTX 960M’s 80.19 GB/s, a critical advantage for texture-heavy scenes and high-detail settings.

The GTX 960M, on the other hand, wins in scenarios where power efficiency and physical size are the primary constraints. Its 75 W TDP is less than half of the GTX 760’s 170 W, making it suitable for thin-and-light laptops where cooling and battery life are at a premium. The MXM Module form factor and lack of power connectors mean it can be integrated into portable designs that cannot accommodate the GTX 760’s dual-slot, 241 mm (9.5 inches) length and 2x 6-pin power connector requirement. While it loses on performance, the GTX 960M is the only one of the two that can function in a mobile environment. Its 4 GB VRAM capacity is also double that of the GTX 760, which could be beneficial for certain workloads that need more memory capacity rather than bandwidth, even if the bus width and bandwidth are significantly lower.

Specification Differences

The specification sheets for these two cards show stark contrasts in nearly every category. The GTX 960M uses the GM107 chip, while the GTX 760 uses the GK104 chip. The GTX 760 has a massive hardware resource advantage: 1152 shading units, 96 TMUs, and 32 ROPs, versus the GTX 960M’s 640 shading units, 40 TMUs, and 16 ROPs. This explains the GTX 760’s higher pixel rate of 24.77 GPixel/s and texture rate of 99.07 GTexel/s, both of which dwarf the GTX 960M’s 18.82 GPixel/s and 47.04 GTexel/s. The FP32 performance follows the same pattern, with the GTX 760 delivering 2.378 TFLOPS against the GTX 960M’s 1.505 TFLOPS.

Memory is another area of divergence. The GTX 960M offers 4 GB of GDDR5 on a 128-bit bus, resulting in 80.19 GB/s of bandwidth. The GTX 760 offers 2 GB of GDDR5 on a 256-bit bus, resulting in 192.3 GB/s of bandwidth. The clock speeds are closer, with the GTX 960M running at a base of 1097 MHz and a boost of 1176 MHz, while the GTX 760 runs at a base of 980 MHz and a boost of 1032 MHz. The GTX 960M has higher clock speeds, but the GTX 760’s superior architecture and wider memory bus more than compensate. The TDP figures are extreme in their difference: 75 W for the GTX 960M versus 170 W for the GTX 760. The GTX 760 also has a suggested PSU of 450 W, while the GTX 960M requires none. The bus interface differs as well, with the GTX 960M using MXM-B (3.0) and the GTX 760 using PCIe 3.0 x16. Display outputs also differ, with the GTX 760 offering 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2, while the GTX 960M’s outputs are listed as "Portable Device Dependent."

Architecture Differences

The architectural divide between these two cards is fundamental. The GTX 960M is built on the Maxwell architecture, using the GM107 chip, while the GTX 760 is built on the older Kepler architecture, using the GK104 chip. Both are manufactured on a 28 nm process at TSMC, but the transistor density differs slightly: the GTX 960M packs 12.6M transistors per mm², while the GTX 760 has 12.0M per mm². The GTX 760 uses 3,540 million transistors spread across a 294 mm² die, whereas the GTX 960M uses a much leaner 1,870 million transistors on a 148 mm² die. This reflects the mobile focus of the GTX 960M, which trades raw compute for power efficiency.

The cache and core configurations are also vastly different. The GTX 760’s 1152 shading units are nearly double the GTX 960M’s 640. The TMU count is more than double (96 vs 40), and the ROP count is exactly double (32 vs 16). These differences directly translate into the performance gap seen in the benchmarks. In terms of API support, both cards support DirectX 12 (11_0) and OpenGL 4.6. However, the Vulkan support differs: the GTX 960M supports Vulkan 1.4, while the GTX 760 supports an older Vulkan 1.2.175. Despite the GTX 960M having a newer Vulkan version, the GTX 760’s hardware is better suited to the workload, as evidenced by its 12551 Vulkan score. The GTX 960M has a newer architecture but is designed for a lower power envelope, while the GTX 760 is a larger, more powerful desktop chip from a previous generation.

The Verdict

The data is unambiguous in its recommendation for raw performance: the NVIDIA GeForce GTX 760 is the superior graphics card. It wins both head-to-head benchmarks, with a particularly crushing 34.3% lead in Vulkan. Its 2.378 TFLOPS of FP32 performance, 192.3 GB/s of memory bandwidth, and higher TMU and ROP counts make it the obvious choice for gaming or compute tasks where performance is the only metric that matters. For a desktop user with room for a dual-slot card and a 450 W PSU, the GTX 760 is the stronger option, despite its lower 2 GB VRAM capacity. The GTX 760’s launch MSRP was 249 USD, which is worth noting as a reference point.

The NVIDIA GeForce GTX 960M is the correct choice for a specific, narrow use case: mobile computing. Its 75 W TDP, MXM Module form factor, and lack of power connectors make it the only viable option for a laptop. A user building a portable system will have no choice but to accept its lower performance, which is 34.3% behind the GTX 760 in Vulkan and 2.2% behind in OpenCL. The GTX 960M’s 4 GB of VRAM is a consolation prize, but the narrower 128-bit bus limits its usefulness. For anyone with a desktop chassis, there is no reason to choose the GTX 960M over the GTX 760 based on the benchmark results. The GTX 760 is the clear winner in every measurable performance category, and the GTX 960M only makes sense when the physical and power constraints of a portable device make the GTX 760 impossible to install.