NVIDIA GeForce GTX 950A vs NVIDIA GeForce GTX 960 Comparison

FAQ

Q: Which GPU has the higher average benchmark score in the database?

A: The NVIDIA GeForce GTX 950A records an average benchmark score of 10273, while the NVIDIA GeForce GTX 960 records an average score of 9273. The GTX 960 has a lower average score, but it is important to note that the two GPUs are benchmarked across different test suites.

Q: What is the performance difference between the two GPUs in the Geekbench OpenCL test?

A: In the Geekbench OpenCL benchmark, the NVIDIA GeForce GTX 960 scores 18925, which is 45.7% ahead of the GTX 950A's score of 10273. This is the only direct head-to-head benchmark recorded in the database.

Q: How does the memory configuration differ between the two cards?

A: The GTX 950A uses 2 GB of DDR3 memory on a 128-bit bus, delivering 32.03 GB/s of bandwidth. The GTX 960 uses 2 GB of GDDR5 memory on the same 128-bit bus width, but delivers 112.2 GB/s of bandwidth, which is significantly higher.

Q: Do both GPUs support the same DirectX version?

A: No. The GTX 950A supports DirectX 12 (11_0), while the GTX 960 supports DirectX 12 (12_1). Both cards support OpenGL 4.6 and Vulkan 1.4.

Q: What are the power requirements for each card?

A: The GTX 950A has a TDP of 75 W and uses no power connectors, while the GTX 960 has a TDP of 120 W and requires a single 6-pin power connector. The GTX 960 also lists a suggested PSU of 300 W.

Q: Which GPU has a higher pixel fill rate?

A: The GTX 960 has a pixel rate of 37.70 GPixel/s, which is more than double the GTX 950A's 17.98 GPixel/s.

Where Each One Wins

The benchmark records show a clear split in strengths. The GTX 950A wins on aggregate score when looking at the Geekbench OpenCL result alone, as its single recorded score of 10273 places it in the 48th percentile of all GPUs. The GTX 960, by contrast, sits in the 45th percentile with an average score of 9273.

However, the direct comparison tells a different story. In the only head-to-head benchmark available, Geekbench OpenCL, the GTX 960 beats the GTX 950A by 45.7%. The GTX 950A's higher average score comes from the fact that its benchmark portfolio consists solely of that one OpenCL test, whereas the GTX 960's average includes a broader set of tests: 3DMark Steel Nomad DX12 (162), Geekbench Metal (8773), Geekbench OpenCL (18925), and Geekbench Vulkan (9231).

The GTX 950A wins on efficiency metrics. Its 75 W TDP is well below the GTX 960's 120 W, and it requires no external power connector. The GTX 950A also occupies a single MXM module slot, making it suitable for portable or compact systems, while the GTX 960 is a dual-slot card.

The GTX 960 wins on raw compute and memory throughput. Its texture rate of 75.39 GTexel/s is 67.7% higher than the GTX 950A's 44.96 GTexel/s. Its FP32 throughput of 2.413 TFLOPS is 67.7% higher than the GTX 950A's 1,438.7 GFLOPS. Memory bandwidth is the largest gap: 112.2 GB/s versus 32.03 GB/s, a 250% advantage.

Architecture Differences

Both GPUs are built by NVIDIA on TSMC's 28 nm process, but they use different chips and different versions of the Maxwell architecture. The GTX 950A is based on the GM107 chip, which uses the original Maxwell architecture. The GTX 960 uses the GM206 chip, which is Maxwell 2.0.

The transistor counts differ substantially. The GM107 chip in the GTX 950A packs 1,870 million transistors on a 148 mm² die, resulting in a transistor density of 12.6M per mm². The GM206 chip in the GTX 960 packs 2,940 million transistors on a 228 mm² die, with a density of 12.9M per mm². The density is nearly identical, but the GTX 960's larger die accommodates far more hardware.

The GTX 960 has 1024 shading units, 64 texture mapping units, and 32 ROPs. The GTX 950A has 640 shading units, 40 TMUs, and 16 ROPs. The GTX 960 thus has 60% more shading units, 60% more TMUs, and double the ROPs.

The memory subsystem differs not just in type but in effective clock. The GTX 950A runs memory at 1001 MHz with 2 Gbps effective, while the GTX 960 runs memory at 1753 MHz with 7 Gbps effective. Both use a 128-bit bus, but the GTX 960's GDDR5 memory achieves 112.2 GB/s versus the GTX 950A's 32.03 GB/s.

The GTX 960 has a higher DirectX feature level (12_1 versus 11_0), which reflects the architectural update in Maxwell 2.0. Both GPUs support OpenGL 4.6 and Vulkan 1.4. Neither GPU includes ray tracing cores or tensor cores.

Specification Differences

The two cards differ across nearly every major specification category. The GTX 950A has a base clock of 993 MHz and a boost clock of 1124 MHz. The GTX 960 has a base clock of 1127 MHz and a boost clock of 1178 MHz. The GTX 960 runs 13.5% higher at base and 4.8% higher at boost.

Memory type is a fundamental split: DDR3 on the GTX 950A versus GDDR5 on the GTX 960. Both have 2 GB capacity and a 128-bit bus, but the GTX 960's memory clock of 1753 MHz (7 Gbps effective) is far above the GTX 950A's 1001 MHz (2 Gbps effective). Bandwidth tells the story: 112.2 GB/s versus 32.03 GB/s.

Compute resources differ by 60% in shading units and TMUs, and 100% in ROPs. Pixel rate is 37.70 GPixel/s on the GTX 960 versus 17.98 GPixel/s on the GTX 950A. Texture rate is 75.39 GTexel/s versus 44.96 GTexel/s. FP32 is 2.413 TFLOPS versus 1,438.7 GFLOPS.

Power and physical specifications diverge sharply. The GTX 950A is a 75 W MXM module with no power connectors, while the GTX 960 is a 120 W dual-slot card requiring one 6-pin connector and a 300 W suggested PSU. The GTX 960 is 241 mm in length. The GTX 950A lists no dimensions in the database.

The bus interface also differs: the GTX 950A uses MXM-B (3.0), while the GTX 960 uses PCIe 3.0 x16. Display outputs are "Portable Device Dependent" on the GTX 950A, while the GTX 960 offers 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.2.

Release timing is close: the GTX 960 launched on January 21, 2015, and the GTX 950A launched on March 12, 2015. Both are end-of-life. The GTX 960's predecessor is the GeForce 700 series and its successor is GeForce 10, while the GTX 950A's predecessor is the GeForce 800A series.

Head-to-Head Benchmarks

The database contains one direct head-to-head benchmark between these two GPUs: Geekbench OpenCL. The GTX 960 scores 18925, and the GTX 950A scores 10273. The delta is -45.7% from the GTX 960's perspective, meaning the GTX 950A trails by 45.7%. This is a decisive win for the GTX 960.

Beyond the direct comparison, the GTX 960's other benchmark results provide context. Its Geekbench Metal score is 8773, and its Geekbench Vulkan score is 9231. Its 3DMark Steel Nomad DX12 result is 162. The GTX 950A has no recorded results for these tests, so no direct comparison is possible.

The GTX 950A's percentile ranking of 48 versus the GTX 960's 45 indicates that the GTX 950A sits in a slightly higher position relative to all GPUs in the database. However, this is driven by the test mix alone. The GTX 950A's average score of 10273 comes from a single OpenCL run, while the GTX 960's average of 9273 is pulled down by its much lower scores in Metal, Vulkan, and 3DMark Steel Nomad.

Nearest rival data reinforces the GTX 960's standing. The GTX 960 sits within 0.6% of the AMD Radeon Vega 8 (9221), within 0.2% of the NVIDIA GeForce GTX 465 (9294), and within 0.3% of the NVIDIA GeForce GTX 850M (9302). The GTX 950A, meanwhile, sits within 2% of the AMD Radeon R9 M375 (10070) and within 0.9% of the AMD Radeon RX 6500M (10362). These rival clusters show that the two NVIDIA cards occupy very different performance tiers despite their similar names.

The largest measurable advantage in the head-to-head data is the 45.7% OpenCL gap. The largest theoretical advantages, based on specification deltas, are the 250% memory bandwidth increase and the 100% ROP increase for the GTX 960.

The Verdict

The data indicates that the NVIDIA GeForce GTX 960 is the stronger GPU for raw performance. Its 45.7% lead in the only shared benchmark, combined with its substantially higher shading unit count, TMU count, ROP count, pixel rate, texture rate, and FP32 throughput, leaves little ambiguity about which card renders faster.

The GTX 950A is not without purpose. Its 75 W TDP, MXM form factor, and lack of power connectors make it a fit for compact or portable systems where the GTX 960's dual-slot, 120 W, 6-pin design would not work. Its 48th percentile ranking also suggests it holds up reasonably well in the aggregate database ranking, though that ranking is based on a single test.

Users who need maximum compute throughput, higher DirectX feature level support (12_1 versus 11_0), and vastly higher memory bandwidth should choose the GTX 960. The 112.2 GB/s bandwidth is the single largest functional difference between the two cards, and it directly impacts texture streaming and high-resolution rendering.

Users constrained by power, space, or expansion options should choose the GTX 950A. The MXM-B interface, 75 W TDP, and portable-device-dependent outputs indicate this card was designed for laptops or small-form-factor systems, not desktop towers.

The GTX 960 has a recorded 3DMark Steel Nomad DX12 score and Vulkan and Metal results; the GTX 950A has none of these. For modern API workloads, the GTX 960 is the only one of the two with database evidence of DX12 capability, and its DirectX 12_1 feature level gives it a hardware-level advantage.

In summary: the GTX 960 wins every direct performance comparison in the database. The GTX 950A wins on power efficiency and form factor suitability. Choose based on the physical and power constraints of the target system, not on benchmark averages alone. The GTX 960's launch MSRP was 199 USD.