NVIDIA GeForce GTX 1660 SUPER vs NVIDIA GeForce GTX 960A Comparison

The NVIDIA GeForce GTX 1660 SUPER is a Turing-architecture desktop card from the GeForce 16 generation, while the NVIDIA GeForce GTX 960A is a Maxwell-architecture mobile module from the GeForce 900A line. The data shows a decisive performance gap: the 1660 SUPER holds an average benchmark score of 12,986 against the 960A’s 11,998, placing both in the 53rd and 51st percentiles of all GPUs respectively. Despite the 960A’s lower raw score, its nearestRivals list includes far more powerful cards like the GTX 1080 and RX 7800 XT, indicating its single benchmark result is an outlier in the database.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 1660 SUPER scores 12,986 on average, which is 988 points higher than the GTX 960A’s 11,998. This puts the 1660 SUPER in the 53rd percentile of all GPUs, while the 960A sits in the 51st percentile.

Q: How big is the performance difference in the only shared benchmark?

A: In Geekbench OpenCL, the GTX 1660 SUPER scores 52,490 versus the GTX 960A’s 11,998. That is a 337.5% advantage for the 1660 SUPER, meaning it delivers more than four times the compute performance in that test.

Q: What are the closest rivals to each card according to the data?

A: The GTX 1660 SUPER’s nearest rival is the NVIDIA Tesla M2090, which scores 13,075 (0.7% higher), followed by the RTX 3050 Ti Mobile at 12,940 (0.4% lower). The GTX 960A’s closest rival is the GTX 1080 at 11,960 (0.3% higher), with the RX 7800 XT trailing by 3.2% at 11,627.

Q: Do both cards support the same DirectX version?

A: No. The GTX 1660 SUPER supports DirectX 12 (12_1), while the GTX 960A supports DirectX 12 (11_0). Both cards support OpenGL 4.6 and Vulkan 1.4.

Q: Which card has more memory and a wider memory bus?

A: The GTX 1660 SUPER has 6 GB of GDDR6 memory on a 192-bit bus, yielding 336.0 GB/s bandwidth. The GTX 960A has 2 GB of GDDR5 on a 128-bit bus, providing only 80.19 GB/s.

Q: What is the form factor difference between the two cards?

A: The GTX 1660 SUPER is a dual-slot PCIe 3.0 x16 card measuring 229 mm in length, while the GTX 960A is an MXM Module using an MXM-B (3.0) interface with no standard dimensions listed.

The Verdict

The GTX 1660 SUPER is the clear choice for any desktop build requiring modern gaming or compute performance. Its average score of 12,986 is 8.2% higher than the 960A’s 11,998, and it wins the only head-to-head benchmark by a 337.5% margin. The 960A, however, is a mobile-only MXM module with no display outputs of its own, so it is not a direct purchase option for standard PC builders. Data suggests the 960A’s single Geekbench OpenCL score of 11,998 places it near desktop cards like the GTX 1080 (11,960) and RX 6500 XT (11,842), but that result is likely misleading given its 640 shading units and 1.505 TFLOPS FP32 throughput. For anyone choosing between these two in a compatible system, the 1660 SUPER wins on every measurable axis: memory capacity (6 GB vs 2 GB), bandwidth (336.0 GB/s vs 80.19 GB/s), and raw compute (5.027 TFLOPS vs 1.505 TFLOPS). The 960A only makes sense in legacy MXM laptops where its 75 W TDP and slotless power design are required.

Head-to-Head Benchmarks

The database contains exactly one shared benchmark between these two cards: Geekbench OpenCL. In that test, the GTX 1660 SUPER scores 52,490, while the GTX 960A manages 11,998. The delta is 337.5% in favor of the 1660 SUPER. To put that in context, the 1660 SUPER’s result is roughly 4.4 times higher. This single data point dominates the comparison, but it aligns with the broader specification gap. The 1660 SUPER’s FP32 throughput of 5.027 TFLOPS is 3.34 times the 960A’s 1.505 TFLOPS, and its texture rate of 157.1 GTexel/s is 3.34 times the 960A’s 47.04 GTexel/s. The pixel rate gap is even larger: 85.68 GPixel/s versus 18.82 GPixel/s, a 4.55x difference. While the head-to-head table shows only one win for the 1660 SUPER, the underlying performance metrics all point in the same direction. The 960A’s only benchmark result is its OpenCL score, so there is no data on DirectX performance, compute workloads beyond OpenCL, or 2D rendering for that card.

Specification Differences

The two cards differ across nearly every core specification. The GTX 1660 SUPER uses the TU116 chip with 6,600 million transistors on a 284 mm² die, while the GTX 960A uses the GM107 chip with 1,870 million transistors on a 148 mm² die. Shading units: 1,408 versus 640. Texture mapping units: 88 versus 40. Raster output units: 48 versus 16. Clock speeds: the 1660 SUPER runs at a 1530 MHz base and 1785 MHz boost, while the 960A runs at 1097 MHz base and 1176 MHz boost. Memory is 6 GB GDDR6 at 1750 MHz (14 Gbps effective) on a 192-bit bus for the 1660 SUPER, versus 2 GB GDDR5 at 1253 MHz (5 Gbps effective) on a 128-bit bus for the 960A. Bandwidth is 336.0 GB/s versus 80.19 GB/s. Power draw is 125 W with a 1x 8-pin connector and 300 W suggested PSU for the 1660 SUPER, whereas the 960A draws 75 W with no power connectors and no suggested PSU. The 1660 SUPER is dual-slot PCIe 3.0 x16 with 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a outputs. The 960A is an MXM-B (3.0) module with portable-device-dependent outputs. The 1660 SUPER has a launch MSRP of 229 USD; the 960A has no launch MSRP listed.

Architecture Differences

The GTX 1660 SUPER is built on TSMC’s 12 nm process with a Turing architecture, achieving a transistor density of 23.2 million transistors per mm². The GTX 960A uses TSMC’s 28 nm process with a Maxwell architecture, resulting in a density of 12.6 million transistors per mm². This node advantage is significant: the 1660 SUPER packs 3.5 times more transistors into a die that is only 1.92 times larger. The 1660 SUPER supports FP16 compute at 10.05 TFLOPS with a 2:1 ratio, whereas the 960A has no FP16 capability listed. Neither card has ray tracing cores or tensor cores. Both support DirectX 12, OpenGL 4.6, and Vulkan 1.4, but the 1660 SUPER’s DirectX 12_1 feature level is higher than the 960A’s 11_0. The 1660 SUPER’s memory clock is 1750 MHz (14 Gbps effective) on GDDR6, while the 960A’s is 1253 MHz (5 Gbps effective) on GDDR5. The 1660 SUPER’s generation is GeForce 16 with a predecessor of GeForce 10 and successor of GeForce 20. The 960A’s generation is GeForce 900A with a predecessor of GeForce 800A and no successor listed. The 1660 SUPER was released later, as evidenced by its position in the 16-series lineup, while the 960A belongs to the older 900A mobile series.

Where Each One Wins

The GTX 1660 SUPER wins in every scenario where performance matters. Its 337.5% lead in Geekbench OpenCL makes it the obvious choice for compute-heavy tasks like OpenCL-accelerated rendering or physics simulation. The 6 GB memory capacity and 336.0 GB/s bandwidth support higher-resolution textures and larger datasets than the 960A’s 2 GB and 80.19 GB/s. The 1660 SUPER’s 5.027 TFLOPS FP32 rate and 157.1 GTexel/s texture rate handle modern game workloads at higher settings. Its 85.68 GPixel/s pixel rate also enables smoother high-refresh-rate 1080p or entry-level 1440p gaming. The 960A’s wins are limited to power efficiency and form factor. Its 75 W TDP is 40% lower than the 1660 SUPER’s 125 W, and its MXM module design with no power connectors suits thin laptops or embedded systems where the 1660 SUPER’s dual-slot, 229 mm length and 8-pin connector cannot fit. The 960A’s nearestRivals list includes the GTX 1080 and RX 7800 XT, but those comparisons are based on its single OpenCL score and do not reflect real-world gaming parity. For desktop users, the 1660 SUPER is the only viable option. For mobile or low-power industrial systems requiring an MXM form factor, the 960A is the sole choice, despite its 1.505 TFLOPS FP32 ceiling and 18.82 GPixel/s pixel rate.