NVIDIA GeForce GTX 1070 Ti vs NVIDIA GeForce GTX 960A Comparison

Where Each One Wins

The recorded benchmark data splits these two NVIDIA mobile and desktop parts along very clear lines. The NVIDIA GeForce GTX 1070 Ti takes the sole head-to-head victory, winning the only directly comparable test by a wide margin. The NVIDIA GeForce GTX 960A, by contrast, does not register a single win in any shared workload, and its available benchmark coverage is far thinner than that of its larger sibling.

Looking at the broader database results, the GTX 1070 Ti posts an average benchmark score of 14277, which places it in the 56th percentile of all GPUs tracked. Its nearest rivals in the database include the Intel Iris Xe MAX Graphics at 14315 (0.3% ahead), the AMD Radeon Vega 11 at 14352 (0.5% ahead), the NVIDIA GeForce GTX TITAN at 14373 (0.7% ahead), and the AMD Radeon RX Vega 11 at 14385 (0.7% ahead). The GTX 1070 Ti sits essentially in the middle of that cluster, slightly behind each of those four parts but within a single percentage point of all of them. That positioning indicates a GPU that is competitive with a well-known set of mainstream and older high-end parts, rather than one that dominates its immediate neighborhood.

The GTX 960A, on the other hand, has an average benchmark score of 11998 and sits in the 51st percentile of all GPUs. Its nearest rivals in the database are far more powerful-sounding names: the NVIDIA GeForce GTX 1080 at 11960 (0.3% behind), the AMD Radeon RX 6500 XT at 11842 (1.3% behind), the NVIDIA GeForce GTX 1660 at 11680 (2.7% behind), and the AMD Radeon RX 7800 XT at 11627 (3.2% behind). This is a curious grouping, because the GTX 960A actually leads all four of those much newer or higher-tier parts in average score, despite being an older, lower-end mobile chip. The data suggests that the GTX 960A's single recorded benchmark result is comparatively strong for its class, or that the database's comparison pool for this GPU is limited.

In terms of wins, the GTX 1070 Ti takes the only head-to-head benchmark (Geekbench OpenCL) with a score of 49219 against the GTX 960A's 11998, a delta of 310.2%. The GTX 960A wins nothing in the shared test set. Therefore, the use-case split is straightforward: the GTX 1070 Ti is the choice for any workload that involves the tested OpenCL compute path, while the GTX 960A offers no recorded advantage in any common benchmark. For practical purposes, the GTX 1070 Ti is the stronger part across the board in the database, and the GTX 960A's role is limited to the niche mobile form factor where it appears.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 1070 Ti has an average benchmark score of 14277, while the NVIDIA GeForce GTX 960A has an average benchmark score of 11998. The GTX 1070 Ti leads by roughly 19%.

Q: How does the GTX 1070 Ti compare to its nearest rivals?

A: The GTX 1070 Ti's nearest rivals are the Intel Iris Xe MAX Graphics (14315, 0.3% ahead), the AMD Radeon Vega 11 (14352, 0.5% ahead), the NVIDIA GeForce GTX TITAN (14373, 0.7% ahead), and the AMD Radeon RX Vega 11 (14385, 0.7% ahead). The GTX 1070 Ti trails all four but by less than one percentage point in each case.

Q: What is the single head-to-head benchmark result between the two cards?

A: The only head-to-head test in the database is Geekbench OpenCL, where the GTX 1070 Ti scores 49219 and the GTX 960A scores 11998. That gives the GTX 1070 Ti a 310.2% advantage.

Q: Does the GTX 960A have any benchmark wins over the GTX 1070 Ti?

A: No. The GTX 960A records zero wins in the head-to-head comparison, while the GTX 1070 Ti records one win (the Geekbench OpenCL test).

Q: How does the GTX 960A perform relative to its own nearest rivals?

A: The GTX 960A's nearest rivals include the NVIDIA GeForce GTX 1080 (11960, 0.3% behind), the AMD Radeon RX 6500 XT (11842, 1.3% behind), the NVIDIA GeForce GTX 1660 (11680, 2.7% behind), and the AMD Radeon RX 7800 XT (11627, 3.2% behind). The GTX 960A actually outscores all four of those parts.

Q: What percentile rank does each GPU hold in the database?

A: The GTX 1070 Ti is in the 56th percentile of all GPUs, while the GTX 960A is in the 51st percentile. Both sit slightly above the median, but the GTX 1070 Ti is ranked higher.

Head-to-Head Benchmarks

The database contains exactly one direct comparison between the NVIDIA GeForce GTX 1070 Ti and the NVIDIA GeForce GTX 960A: the Geekbench OpenCL test. In that workload, the GTX 1070 Ti produces a score of 49219, while the GTX 960A produces a score of 11998. The resulting delta is 310.2% in favor of the GTX 1070 Ti. That is not a marginal difference; it is a multiple of roughly four times the raw score. OpenCL is a general-purpose compute API, so this result speaks to raw shader and memory throughput rather than gaming-specific optimization. The GTX 1070 Ti's much larger shading unit count, higher clock speeds, and wider memory bus all contribute to this outcome.

To put that single result in context, the GTX 1070 Ti's OpenCL score of 49219 is also far above its own average benchmark score of 14277, which suggests that OpenCL is a particularly favorable workload for this GPU. The GTX 960A's OpenCL score of 11998 is essentially identical to its average score of 11998, because that is the only benchmark recorded for it. So while the head-to-head comparison is limited to one test, the magnitude of the GTX 1070 Ti's win is decisive. There is no recorded test where the GTX 960A comes close.

The GTX 1070 Ti also shows strength in other database benchmarks, even though those are not directly compared against the GTX 960A. Its Passmark G3D score is 14674, its Geekbench Vulkan score is 61006, and its Geekbench Metal score is 22180. The GTX 960A has no corresponding records in those tests, so a full multi-workload comparison is impossible. Nevertheless, the single shared data point is unambiguous: the GTX 1070 Ti is significantly faster in compute-heavy OpenCL tasks, and the GTX 960A offers no countervailing victory anywhere in the database.

Specification Differences

The two GPUs differ on nearly every measurable specification. The GTX 1070 Ti uses the GP104 chip built on a 16 nm process at TSMC, while the GTX 960A uses the GM107 chip built on a 28 nm process at TSMC. The transistor counts are 7,200 million versus 1,870 million, and the die sizes are 314 mm² versus 148 mm². Transistor density is 22.9M per mm² for the GTX 1070 Ti and 12.6M per mm² for the GTX 960A, reflecting the newer manufacturing node.

Clock speeds diverge substantially. The GTX 1070 Ti has a base clock of 1607 MHz and a boost clock of 1683 MHz, while the GTX 960A has a base clock of 1097 MHz and a boost clock of 1176 MHz. Memory clocks also differ: the GTX 1070 Ti runs at 2002 MHz with 8 Gbps effective, while the GTX 960A runs at 1253 MHz with 5 Gbps effective.

Memory configuration is a major separator. The GTX 1070 Ti carries 8 GB of GDDR5 on a 256-bit bus, yielding a bandwidth of 256.3 GB/s. The GTX 960A carries 2 GB of GDDR5 on a 128-bit bus, yielding a bandwidth of 80.19 GB/s. That is a threefold difference in memory bandwidth, which directly affects high-resolution textures and compute workloads.

The compute resources are also vastly different. The GTX 1070 Ti has 2432 shading units, 152 texture mapping units, and 64 ROPs. The GTX 960A has 640 shading units, 40 TMUs, and 16 ROPs. Pixel rates are 107.7 GPixel/s for the GTX 1070 Ti and 18.82 GPixel/s for the GTX 960A. Texture rates are 255.8 GTexel/s and 47.04 GTexel/s, respectively. FP32 throughput is 8.186 TFLOPS for the GTX 1070 Ti, while the GTX 960A manages 8.186 TFLOPS is not a typo; it is the GTX 1070 Ti's FP32 figure. The GTX 960A has an FP32 throughput of 1.505 TFLOPS. The GTX 1070 Ti also lists an FP16 rate of 127.9 GFLOPS (1:64), while the GTX 960A has no recorded FP16 value.

Power and physical specifications differ as well. The GTX 1070 Ti has a TDP of 180 W, a dual-slot width, a single 8-pin power connector, a suggested PSU of 450 W, and a PCIe 3.0 x16 bus interface. The GTX 960A has a TDP of 75 W, an MXM module form factor, no power connectors, no suggested PSU, and an MXM-B (3.0) bus interface. The GTX 1070 Ti's dimensions are 267 mm in length, 112 mm in height, and 40 mm in width, while the GTX 960A has no recorded dimensions. Display outputs differ too: the GTX 1070 Ti offers 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.1a, while the GTX 960A's outputs are portable device dependent. The GTX 1070 Ti supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The GTX 960A supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4.

Architecture Differences

The GTX 1070 Ti is built on NVIDIA's Pascal architecture, while the GTX 960A is built on the older Maxwell architecture. Pascal is the GeForce 10-series generation, and the GTX 1070 Ti's predecessor is the GeForce 900 series, with the GeForce 20 series as its successor. The GTX 960A belongs to the GeForce 900A generation, with the GeForce 800A as its predecessor and no recorded successor.

The process node difference is fundamental: 16 nm versus 28 nm, both at TSMC. That explains the dramatic transistor density improvement, 22.9M per mm² versus 12.6M per mm², and the much larger total transistor count on the GTX 1070 Ti despite only a modest die size difference. The GTX 1070 Ti packs 7,200 million transistors into 314 mm², while the GTX 960A packs 1,870 million into 148 mm².

In terms of compute features, both GPUs lack dedicated ray tracing cores and tensor cores, as neither architecture includes them. The GTX 1070 Ti supports DirectX 12 at feature level 12_1, whereas the GTX 960A supports DirectX 12 at feature level 11_0, indicating a lower tier of DirectX 12 feature support. Both support OpenGL 4.6 and Vulkan 1.4, so the API surface is otherwise identical.

The GTX 960A's FP16 capability is not recorded, while the GTX 1070 Ti has a limited FP16 rate of 127.9 GFLOPS at a 1:64 ratio, meaning FP16 is heavily de-emphasized in Pascal. Maxwell, by contrast, typically has no dedicated FP16 path. The GTX 1070 Ti's memory clock of 2002 MHz with 8 Gbps effective is a hallmark of the Pascal generation, designed to pair high bandwidth with the GDDR5 standard. The GTX 960A's 1253 MHz memory clock with 5 Gbps effective is more typical of the Maxwell era.

The GTX 1070 Ti is a full PCIe 3.0 x16 desktop card requiring an 8-pin power connector and a 450 W PSU recommendation, while the GTX 960A is an MXM module using a 3.0 bus interface with no power connector and no PSU guidance, reflecting its mobile laptop design. The GTX 1070 Ti's 16 nm process and 180 W TDP versus the GTX 960A's 28 nm process and 75 W TDP shows the trade-off between performance headroom and mobility constraints. Ultimately, the architecture gap is generational and architectural: Pascal, with a newer node, more transistors, more memory, and higher clocks, against Maxwell, with an older, smaller design optimized for low-power mobile use without direct headroom.