NVIDIA GeForce GTX 1080 vs NVIDIA GeForce GTX 965M Comparison

Head-to-Head Benchmarks

The recorded data contains only two shared benchmark tests between the NVIDIA GeForce GTX 965M and the NVIDIA GeForce GTX 1080, and the GTX 1080 wins both. The largest margin appears in Geekbench OpenCL, where the GTX 1080 scores 51,204 against the GTX 965M’s 14,509. That is a delta of -71.7% from the GTX 1080’s perspective, meaning the GTX 965M trails by roughly three and a half times. In raw terms, the GTX 1080 delivers about 3.5x the OpenCL throughput, a gap that reflects the fundamental separation between a mobile-class chip and a desktop flagship.

The second shared test, Geekbench Vulkan, is less lopsided but still decisive. The GTX 1080 posts 30,398, while the GTX 965M manages 14,299. The delta here is -53%, so the GTX 965M scores just under half of the GTX 1080’s Vulkan result. Interestingly, the GTX 965M’s OpenCL and Vulkan scores are nearly identical (14,509 vs 14,299), suggesting its compute performance is consistent across APIs. The GTX 1080, by contrast, shows a notable API gap: its OpenCL score is 68% higher than its Vulkan score, indicating that OpenCL workloads extract more from its Pascal architecture.

Looking at the broader database, the GTX 965M’s average benchmark score is 14,404, placing it in the 56th percentile of all GPUs. Its nearest rivals include the AMD Radeon RX Vega 11 (14,385, 0.1% behind), the NVIDIA GeForce GTX TITAN (14,373, 0.2% behind), and the AMD Radeon Vega 11 (14,352, 0.4% behind). These are extremely tight margins, meaning the GTX 965M sits in a dense cluster of mid-range performers. The GTX 1080, meanwhile, has an average score of 11,960, which lands it in the 51st percentile. That seems counterintuitive given its head-to-head dominance, but its nearest rivals include the NVIDIA GeForce GTX 960A (11,998, -0.3%), the AMD Radeon RX 6500 XT (11,842, 1%), and the NVIDIA GeForce GTX 1660 (11,680, 2.4%). The GTX 1080’s average is dragged down by its PassMark legacy tests, which are not apples-to-apples with the GTX 965M’s limited benchmark set.

The wins tally is unambiguous: the GTX 1080 claims 2 wins, the GTX 965M claims 0. No single test in the database favors the older mobile chip.

FAQ

Q: How much faster is the GTX 1080 in OpenCL?

A: The GTX 1080 scores 51,204 in Geekbench OpenCL versus the GTX 965M’s 14,509, a delta of -71.7% from the GTX 1080’s side. In practical terms, the GTX 1080 is about 3.5x faster in this workload.

Q: Is the GTX 965M competitive in Vulkan?

A: It is not competitive against the GTX 1080. Its Vulkan score of 14,299 is roughly 47% of the GTX 1080’s 30,398. However, the GTX 965M’s Vulkan result is close to its OpenCL result, suggesting balanced compute performance within its own class.

Q: What percentile does each GPU sit at globally?

A: The GTX 965M is in the 56th percentile of all GPUs, while the GTX 1080 is in the 51st percentile. This is based on average benchmark scores across different test suites.

Q: Are the GTX 965M’s closest rivals similarly performing?

A: Yes. The AMD Radeon RX Vega 11 scores 14,385 (0.1% behind), the NVIDIA GeForce GTX TITAN scores 14,373 (0.2% behind), and the AMD Radeon Vega 11 scores 14,352 (0.4% behind). The GTX 965M is effectively tied with all three.

Q: Does the GTX 1080 have any weak benchmark results?

A: Its PassMark scores are low relative to its Geekbench results. For example, PassMark DirectX 10 yields 93, DirectX 11 yields 124, and DirectX 9 yields 211. These are legacy tests and do not reflect modern workloads.

Q: Which GPU has a higher average benchmark score?

A: The GTX 965M has a higher average at 14,404 versus the GTX 1080’s 11,960. This is misleading, however, because the GTX 1080’s average includes many more tests, several of which are older DirectX benchmarks.

Architecture Differences

The two chips come from entirely different architectural generations. The GTX 965M uses the GM204 die, built on Maxwell 2.0, while the GTX 1080 uses the GP104 die, built on Pascal. The manufacturing process moved from 28 nm on Maxwell to 16 nm on Pascal, both courtesy of TSMC. That node shrink is directly visible in transistor density: the GTX 965M packs 5,200 million transistors on a 398 mm² die, yielding 13.1 million transistors per square millimeter. The GTX 1080 packs 7,200 million transistors on a smaller 314 mm² die, achieving 22.9 million transistors per square millimeter. The Pascal chip is physically smaller yet contains nearly 40% more transistors, a clear sign of the density jump.

The compute architecture differs as well. The GTX 965M has 1,024 shading units, 64 texture mapping units, and 32 raster output pipelines. The GTX 1080 more than doubles the shading units to 2,560, raises TMUs to 160, and doubles ROPs to 64. Neither card has dedicated ray tracing cores or tensor cores; both rely on traditional CUDA cores for rendering and compute. The GTX 1080 does support FP16 at 138.6 GFLOPS with a 1:64 ratio, while the GTX 965M has no listed FP16 capability. This is a minor addition for the Pascal part, relevant mostly for mixed-precision workloads.

Memory architecture is another differentiator. The GTX 965M uses 2 GB of GDDR5 on a 128-bit bus, yielding 80.19 GB/s of bandwidth. The GTX 1080 uses 8 GB of GDDR5X on a 256-bit bus, delivering 320.3 GB/s. That is a 4x increase in memory capacity and a 4x increase in bandwidth, which directly impacts texture-heavy and high-resolution workloads. The GTX 1080’s memory clock is listed at 1251 MHz with 10 Gbps effective, while the GTX 965M runs at 1253 MHz with 5 Gbps effective. The doubling of effective data rate per pin is a key Pascal improvement.

The GTX 1080 also has a much higher pixel rate (110.9 GPixel/s versus 30.40 GPixel/s) and texture rate (277.3 GTexel/s versus 60.80 GTexel/s). These are direct consequences of the higher ROP and TMU counts, respectively. The FP32 throughput tells the same story: 8.873 TFLOPS for the GTX 1080 versus 1.946 TFLOPS for the GTX 965M.

Specification Differences

The two GPUs differ across nearly every specification field. The GTX 965M has a base clock of 924 MHz and a boost clock of 950 MHz, while the GTX 1080 runs at 1607 MHz base and 1733 MHz boost. That is a 74% higher base clock and an 82% higher boost clock for the Pascal part. The GTX 965M has no TDP listed, while the GTX 1080 is rated at 180 W with a suggested PSU of 450 W. The GTX 965M uses an MXM-B (3.0) bus interface and carries no power connectors, whereas the GTX 1080 uses PCIe 3.0 x16 and requires a single 8-pin connector. The GTX 965M is a single-slot MXM module with portable-device-dependent display outputs; the GTX 1080 is a dual-slot card measuring 267 mm in length, 112 mm in height, and 40 mm in width, with outputs including 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.4a.

Both support DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, so API compatibility is identical. The GTX 965M was released on 2015-01-08, while the GTX 1080 came later on 2016-05-26. The GTX 965M’s predecessor is GeForce 800M and its successor is GeForce 10 Mobile; the GTX 1080’s predecessor is GeForce 900 and its successor is GeForce 20. The GTX 1080 has a launch MSRP of 599 USD, which the database notes once, and the GTX 965M has no listed MSRP. Both are marked as end-of-life production.

Where Each One Wins

The GTX 1080 wins in every measured head-to-head category. For OpenCL compute, it is 3.5x ahead, making it the clear choice for GPU-accelerated tasks like rendering, simulation, or data processing. For Vulkan, it is roughly 2.1x ahead, which translates to better performance in modern Vulkan-based games and applications. The GTX 1080 also wins on raw bandwidth, pixel rate, texture rate, and FP32 throughput, all of which favor gaming at high resolutions and detail settings.

The GTX 965M, by contrast, has no benchmark wins in the shared tests. Its strengths are relative to its own class: it sits in the 56th percentile globally and is virtually tied with the AMD Radeon RX Vega 11, the NVIDIA GeForce GTX TITAN, and the AMD Radeon Vega 11. In the context of older or lighter workloads, such as 2D tasks or legacy DirectX titles, the GTX 965M’s lower power envelope and MXM form factor make it suitable for portable devices where the GTX 1080 cannot physically fit. The GTX 1080’s PassMark G2D score of 888 is decent, but the GTX 965M’s mobile nature means it is designed for laptops, not desktop towers.

For users constrained to a laptop chassis, the GTX 965M is the only option of the two. For anyone with a desktop PCIe slot and a 450 W PSU, the GTX 1080 dominates every workload in the data.

The Verdict

The database is unambiguous: the NVIDIA GeForce GTX 1080 is the superior GPU by every measured metric. It wins both head-to-head tests, delivers 3.5x the OpenCL performance, and 2.1x the Vulkan performance. Its architecture advantages, including a smaller 16 nm die with higher transistor density, double the shading units, quadruple the memory bandwidth, and far higher clock speeds, leave no room for the GTX 965M to compete. The GTX 965M does hold a higher global percentile (56th versus 51st), but that reflects its placement among a broader set of GPUs, not its performance relative to the GTX 1080.

The GTX 1080’s average benchmark score is lower than the GTX 965M’s, but this is an artifact of its larger test suite, which includes many legacy PassMark tests that do not represent modern workloads. In the tests that matter for current applications, the GTX 1080 is overwhelmingly ahead. The GTX 965M is a capable mobile part for its era, sitting within 0.6% of its nearest rivals, but it is not in the same performance tier as the GTX 1080.

Who should pick which? The GTX 1080 is the choice for desktop users who need high compute throughput, modern API performance, and large memory capacity. The GTX 965M is the choice for portable systems where the MXM form factor and lack of external power connectors are required. There is no scenario in the recorded data where the GTX 965M outperforms the GTX 1080 in a shared benchmark. The verdict is straightforward: the GTX 1080 wins outright.