NVIDIA GeForce GTX 960A vs NVIDIA GeForce GTX 965M Comparison

Where Each One Wins

The NVIDIA GeForce GTX 965M takes the clear win in the recorded benchmark data. Across the single head-to-head test available in the database, the GTX 965M outperforms the GTX 960A by 20.9% in Geekbench OpenCL. The GTX 965M also holds a higher average benchmark score of 14,404 compared to the GTX 960A's 11,998. That is a decisive margin in compute workloads.

The GTX 965M's advantage comes from its larger configuration. With 1,024 shading units, 64 texture mapping units, and 32 raster output units, it has substantially more processing resources than the GTX 960A's 640 shading units, 40 TMUs, and 16 ROPs. In raw throughput terms, the GTX 965M delivers 1.946 TFLOPS of FP32 compute versus 1.505 TFLOPS for the GTX 960A. That translates into roughly a 29% higher theoretical compute ceiling, which explains the benchmark gap.

For gaming scenarios, the GTX 965M also has a notable edge in fill-rate dependent workloads. Its pixel rate of 30.40 GPixel/s is nearly double the GTX 960A's 18.82 GPixel/s. Texture rate follows a similar pattern: 60.80 GTexel/s for the 965M versus 47.04 GTexel/s for the 960A. These metrics matter in modern game engines that push high resolutions and detailed textures.

The GTX 960A is not without its strengths. It runs at higher clock speeds: 1,097 MHz base and 1,176 MHz boost, compared to 924 MHz base and 950 MHz boost for the GTX 965M. In clock-for-clock comparisons, the 960A is more efficient per cycle. However, the GTX 965M's raw resource advantage more than compensates for the lower clocks. The database shows the GTX 965M wins the only recorded head-to-head test, and its percentile ranking of 56 versus 51 for the GTX 960A indicates it sits higher in the overall GPU distribution.

The GTX 965M is the choice for users who need compute performance, higher fill rates, and better OpenCL results. The GTX 960A remains a capable option for lighter workloads where its lower transistor count and smaller die size may be acceptable trade-offs, but the data does not show any benchmark category where it wins.

Architecture Differences

Both GPUs come from NVIDIA's Maxwell family, but they represent different tiers of that architecture. The GTX 965M uses the GM204 chip, which is the larger, more capable silicon. The GTX 960A uses the GM107 chip, a smaller and less complex design.

The manufacturing process is identical: both are built on TSMC's 28 nm node. However, the chip sizes differ dramatically. The GM204 die measures 398 mm² and packs 5,200 million transistors. The GM107 die is just 148 mm² with 1,870 million transistors. That gives the GTX 965M a transistor density of 13.1M per mm², slightly higher than the GTX 960A's 12.6M per mm². The larger die and higher transistor count enable the GTX 965M to include more shading units, TMUs, and ROPs, as detailed in the specification section.

The GTX 965M is labeled Maxwell 2.0, while the GTX 960A is labeled simply Maxwell. This is a meaningful distinction. Maxwell 2.0, as implemented on GM204, adds features and optimizations over the original Maxwell design found on GM107. Both support DirectX 12, OpenGL 4.6, and Vulkan 1.4, but the feature level differs: the GTX 965M supports DirectX 12 (12_1), while the GTX 960A supports DirectX 12 (11_0). This means the GTX 965M can handle more advanced DirectX 12 feature levels, which can matter in newer titles that utilize tier-1 or tier-2 hardware features.

Memory subsystems are nearly identical. Both cards feature 2 GB of GDDR5 memory on a 128-bit bus, with 80.19 GB/s of bandwidth and a memory clock of 1253 MHz (5 Gbps effective). Neither card supports ray tracing or tensor cores, as both are pre-Ampere designs. The GTX 965M's architecture also allows for higher pixel throughput due to its 32 ROPs versus 16 on the GTX 960A.

Power characteristics differ as well. The GTX 960A has a rated TDP of 75 W, while the GTX 965M has no listed TDP in the database. Both use MXM modules with no external power connectors, and both depend on portable device outputs, meaning the display configuration is determined by the laptop or mobile workstation design.

The GTX 965M belongs to the GeForce 900M generation, while the GTX 960A belongs to the GeForce 900A generation. The GTX 965M was released on January 8, 2015, and the GTX 960A followed on March 12, 2015. Both are end-of-life products. The GTX 965M lists its predecessor as GeForce 800M and successor as GeForce 10 Mobile, while the GTX 960A lists GeForce 800A as its predecessor and no successor.

FAQ

Q: Which GPU has higher raw compute performance in the database measurements?

A: The GTX 965M delivers 1.946 TFLOPS of FP32 compute, which is 29% higher than the GTX 960A's 1.505 TFLOPS. Its average benchmark score of 14,404 versus 11,998 confirms the gap in real-world compute tests.

Q: Do both cards have the same memory configuration?

A: Yes, both feature 2 GB of GDDR5 memory on a 128-bit bus with 80.19 GB/s bandwidth and 1253 MHz memory clock (5 Gbps effective). No difference exists in this area.

Q: Which card supports a higher DirectX feature level?

A: The GTX 965M supports DirectX 12 (12_1), while the GTX 960A supports DirectX 12 (11_0). Both support OpenGL 4.6 and Vulkan 1.4.

Q: How do the clock speeds compare?

A: The GTX 960A runs faster at 1,097 MHz base and 1,176 MHz boost, versus the GTX 965M's 924 MHz base and 950 MHz boost. Despite lower clocks, the GTX 965M wins in benchmark results due to its larger chip.

Q: Are these cards still in production?

A: No, both are marked as end-of-life products. The GTX 965M was released on January 8, 2015, and the GTX 960A on March 12, 2015.

Q: What is the transistor count difference?

A: The GTX 965M uses the GM204 chip with 5,200 million transistors on a 398 mm² die. The GTX 960A uses the GM107 chip with 1,870 million transistors on a 148 mm² die.

Specification Differences

The two GPUs diverge significantly in their core configurations while sharing some memory parameters and interface characteristics.

| Specification | GTX 965M | GTX 960A |

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

| Chip | GM204 | GM107 |

| Architecture | Maxwell 2.0 | Maxwell |

| Generation | GeForce 900M | GeForce 900A |

| Transistors | 5,200 million | 1,870 million |

| Die Size | 398 mm² | 148 mm² |

| Transistor Density | 13.1M / mm² | 12.6M / mm² |

| Base Clock | 924 MHz | 1,097 MHz |

| Boost Clock | 950 MHz | 1,176 MHz |

| Shading Units | 1,024 | 640 |

| TMUs | 64 | 40 |

| ROPs | 32 | 16 |

| Pixel Rate | 30.40 GPixel/s | 18.82 GPixel/s |

| Texture Rate | 60.80 GTexel/s | 47.04 GTexel/s |

| FP32 Compute | 1.946 TFLOPS | 1.505 TFLOPS |

| TDP | Not listed | 75 W |

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

| Release Date | 2015-01-08 | 2015-03-12 |

| Predecessor | GeForce 800M | GeForce 800A |

| Successor | GeForce 10 Mobile | None |

| Avg Benchmark Score | 14,404 | 11,998 |

| Percentile vs All GPUs | 56 | 51 |

Both cards use 28 nm TSMC process, 2 GB GDDR5 memory, 128-bit bus, 80.19 GB/s bandwidth, MXM-B (3.0) bus interface, and have no power connectors. Both list portable-device-dependent display outputs.

Head-to-Head Benchmarks

The database records one head-to-head benchmark between these two GPUs: Geekbench OpenCL. The GTX 965M scores 14,509, while the GTX 960A scores 11,998. That yields a delta of 20.9% in favor of the GTX 965M. This is a substantial margin, and it aligns with the architectural differences between the two chips.

The GTX 965M's victory in Geekbench OpenCL can be attributed directly to its execution resources. With 1,024 shading units versus 640, it processes 60% more shader work per cycle. Even though the GTX 960A boosts to 1,176 MHz versus 950 MHz for the GTX 965M, a 24% clock advantage cannot overcome a 60% shader unit deficit. The GTX 965M's FP32 throughput of 1.946 TFLOPS versus 1.505 TFLOPS means the 965M can complete more floating-point operations per second, which is the core of OpenCL compute workloads.

Texture and pixel throughput also favor the GTX 965M. The 965M's texture rate of 60.80 GTexel/s is 29% higher than the 960A's 47.04 GTexel/s. Its pixel rate of 30.40 GPixel/s is 62% higher than the 960A's 18.82 GPixel/s. These metrics matter for graphics-heavy OpenCL workloads that involve image processing, filtering, or rendering passes.

The GTX 960A's higher clock speeds do give it an edge in latency-sensitive workloads that are clock-bound rather than resource-bound. At 1,176 MHz boost, each of its 640 shading units operates faster than each of the GTX 965M's 1,024 units at 950 MHz. However, the recorded benchmark data shows no test where this advantage translates into a win. The GTX 960A's percentile of 51 places it just above the midpoint of all GPUs, while the GTX 965M's percentile of 56 indicates a stronger overall position.

In terms of nearest rivals, the GTX 965M's average score of 14,404 is 0.1% ahead of the AMD Radeon RX Vega 11 (14,385), 0.2% ahead of the NVIDIA GeForce GTX TITAN (14,373), 0.4% ahead of the AMD Radeon Vega 11 (14,352), and 0.6% ahead of the Intel Iris Xe MAX Graphics (14,315). The GTX 960A's average score of 11,998 is 0.3% ahead of the NVIDIA GeForce GTX 1080 (11,960), 1.3% ahead of the AMD Radeon RX 6500 XT (11,842), 2.7% ahead of the NVIDIA GeForce GTX 1660 (11,680), and 3.2% ahead of the AMD Radeon RX 7800 XT (11,627). These rival comparisons show that the GTX 965M competes in a higher performance tier than the GTX 960A, which sits closer to mid-range desktop parts despite its mobile form factor.

The takeaway from the head-to-head data is unambiguous: the GTX 965M outperforms the GTX 960A by a wide margin in the recorded OpenCL test, and its architectural advantages in shader count, TMUs, ROPs, and compute throughput support that result. The GTX 960A offers higher clocks and a lower TDP, but the GTX 965M's larger GM204 die delivers the performance that matters in benchmark results.