NVIDIA GeForce GTX 1070 Ti vs NVIDIA GeForce GTX 950 Comparison

The NVIDIA GeForce GTX 950 and the NVIDIA GeForce GTX 1070 Ti represent two distinct generations of NVIDIA’s mainstream and performance-tier offerings. The data in the FACT PACK shows a clear generational divide, with the GTX 1070 Ti consistently outperforming the older GTX 950 across every shared benchmark metric. This analysis compares their benchmark scores, architectural differences, and identifies which workloads favor each card, based strictly on the provided data.

Head-to-Head Benchmarks

The benchmark results are unambiguous: the GeForce GTX 1070 Ti wins all three head-to-head comparisons, with no victories for the GTX 950. The largest relative gap appears in the Geekbench Vulkan test, where the GTX 1070 Ti scores 61,006 against the GTX 950’s 16,734. This represents a delta of -72.6% from the perspective of the GTX 950, meaning the newer card delivers roughly 3.6 times the performance in this API-heavy workload. The margin is slightly narrower but still decisive in Geekbench OpenCL, where the GTX 1070 Ti’s 49,219 surpasses the GTX 950’s 15,662 by a delta of -68.2%. In Geekbench Metal, the GTX 1070 Ti posts 22,180 versus 7,172 for the GTX 950, a delta of -67.7%.

These deltas indicate that the GTX 1070 Ti is not merely incrementally faster but operates in a completely different performance tier. For context, the GTX 950’s average benchmark score across all tests is 13,189, which places it at the 53rd percentile of all GPUs. Its nearest rivals include the NVIDIA GeForce GTX 480 with an average score of 13,300 (a delta of -0.8%) and the AMD FirePro M6100 at 13,354 (delta -1.2%). The GTX 1070 Ti, by contrast, averages 14,277 across its benchmark suite, sitting at the 56th percentile. Its nearest rivals are the Intel Iris Xe MAX Graphics (14,315, delta -0.3%) and the AMD Radeon Vega 11 (14,352, delta -0.5%). While the absolute scores are close between the two cards’ respective rival groups, the head-to-head deltas confirm that the GTX 1070 Ti’s advantage over the GTX 950 is far larger than the differences separating each card from its own nearest competitors.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The NVIDIA GeForce GTX 1070 Ti has an average benchmark score of 14,277, compared to the GTX 950’s 13,189. This gives the GTX 1070 Ti a higher percentile ranking at 56 versus 53 for the GTX 950.

Q: How much faster is the GTX 1070 Ti in Geekbench Vulkan?

A: The GTX 1070 Ti scores 61,006 in Geekbench Vulkan, while the GTX 950 scores 16,734. The delta is -72.6% for the GTX 950, indicating the GTX 1070 Ti is approximately 3.6 times faster in this specific test.

Q: Are there any benchmark tests where the GTX 950 wins?

A: No. In the head-to-head benchmarks provided, which include Geekbench Metal, OpenCL, and Vulkan, the GTX 1070 Ti wins all three tests. The GTX 950 records zero wins.

Q: How do the two cards compare in terms of memory bandwidth?

A: The GTX 1070 Ti has a memory bandwidth of 256.3 GB/s, while the GTX 950 has 105.8 GB/s. The GTX 1070 Ti also has a larger memory bus width of 256 bit versus 128 bit for the GTX 950.

Q: What is the difference in shading units between the two cards?

A: The GTX 1070 Ti contains 2,432 shading units, whereas the GTX 950 has 768. This represents a substantial increase in parallel processing capability for the newer card.

Q: Do both cards support the same DirectX version?

A: Yes, both support DirectX 12 (12_1). They also both support OpenGL 4.6 and Vulkan 1.4, according to the specification data.

Where Each One Wins

Based on the benchmark data, the NVIDIA GeForce GTX 1070 Ti is the clear winner in every measurable category where both cards were tested. The GTX 950 does not win a single head-to-head benchmark, so it cannot be recommended for any performance-sensitive workload that appears in the FACT PACK. The GTX 1070 Ti’s dominance spans compute-oriented APIs like OpenCL and Vulkan, as well as Apple’s Metal API, suggesting broad applicability across different software ecosystems.

The GTX 950’s only advantage lies in its physical characteristics and power requirements, which are not benchmark performance metrics but may influence system compatibility. It has a TDP of 90 W versus 180 W for the GTX 1070 Ti, and its suggested PSU is 250 W compared to 450 W. The GTX 950 is also shorter at 202 mm (8 inches) versus 267 mm (10.5 inches) for the GTX 1070 Ti. For users with constrained power supplies or small form factor cases, the GTX 950 is the more accommodating option, but this is not a performance win. In terms of raw compute, the GTX 1070 Ti’s FP32 throughput of 8.186 TFLOPS dwarfs the GTX 950’s 1.825 TFLOPS, and its texture rate of 255.8 GTexel/s is over four times the GTX 950’s 57.02 GTexel/s.

Specification Differences

The most obvious specification gap is in memory configuration. The GTX 1070 Ti ships with 8 GB of GDDR5 memory on a 256-bit bus, yielding 256.3 GB/s of bandwidth. The GTX 950 offers 2 GB of GDDR5 on a 128-bit bus, with 105.8 GB/s. The memory clock also differs: the GTX 1070 Ti runs at 2002 MHz (8 Gbps effective), while the GTX 950 runs at 1653 MHz (6.6 Gbps effective).

Compute resources are similarly lopsided. The GTX 1070 Ti has 2,432 shading units, 152 texture mapping units (TMUs), and 64 raster operation units (ROPs). The GTX 950 has 768 shading units, 48 TMUs, and 32 ROPs. Clock speeds favor the GTX 1070 Ti as well, with a base clock of 1607 MHz and boost of 1683 MHz, versus 1024 MHz base and 1188 MHz boost for the GTX 950.

Power and physical specs differ significantly. The GTX 1070 Ti draws 180 W and requires a 450 W PSU, while the GTX 950 draws 90 W and needs only a 250 W PSU. The GTX 1070 Ti uses a single 8-pin power connector, while the GTX 950 uses a single 6-pin. Both are dual-slot cards, but the GTX 1070 Ti is longer (267 mm vs 202 mm) and has specified height and width dimensions of 112 mm and 40 mm respectively, which the GTX 950 lacks in the data. Display outputs are identical in count (1x DVI, 1x HDMI 2.0, 3x DisplayPort), but the GTX 1070 Ti uses DisplayPort 1.4a versus DisplayPort 1.2 on the GTX 950.

Architecture Differences

The two cards are built on different architectures and process nodes, which explains much of the performance disparity. The GTX 950 uses the GM206 chip, based on Maxwell 2.0 architecture, fabricated on a 28 nm process at TSMC. It contains 2,940 million transistors on a 228 mm² die, for a transistor density of 12.9 million per mm². The GTX 1070 Ti uses the GP104 chip, based on Pascal architecture, fabricated on a 16 nm process, also at TSMC. It packs 7,200 million transistors into a 314 mm² die, achieving a density of 22.9 million per mm².

The jump from Maxwell 2.0 to Pascal brought not only a smaller process node but also architectural refinements. The GTX 1070 Ti’s FP16 throughput is listed at 127.9 GFLOPS (1:64), a feature absent from the GTX 950’s specifications. Both cards lack dedicated ray tracing and tensor cores, as indicated by null values in the data. The GTX 950 belongs to the GeForce 900 generation with a release date of 2015-08-19, while the GTX 1070 Ti is part of the GeForce 10-series, released on 2017-11-01. The GTX 950’s predecessor is GeForce 700 and its successor is GeForce 10; the GTX 1070 Ti’s predecessor is GeForce 900 and its successor is GeForce 20. Both cards are marked as end-of-life in production status.

The architecture difference also shows in pixel and texture rates. The GTX 1070 Ti achieves 107.7 GPixel/s and 255.8 GTexel/s, versus 38.02 GPixel/s and 57.02 GTexel/s for the GTX 950. These figures are direct consequences of the higher core counts and clock speeds enabled by the newer Pascal architecture on a denser process node. The 16 nm node allows for significantly more transistors per area and higher operating frequencies, which the benchmark results reflect across all tested workloads.