NVIDIA GeForce GTX 950M vs NVIDIA GeForce GTX 970 Comparison

Head-to-Head Benchmarks

The benchmark data leaves little room for ambiguity: the NVIDIA GeForce GTX 970 dominates the NVIDIA GeForce GTX 950M in every recorded head-to-head test. In the Geekbench OpenCL workload, the GTX 970 scores 29,982 points against the GTX 950M's 9,745 points, a gap of 67.5 percent in favor of the desktop card. That is not a marginal advantage; it is a generational chasm that places the two products in entirely different performance classes.

The Vulkan results follow the same pattern with almost surgical precision. The GTX 970 returns 20,005 points, while the GTX 950M manages 6,525 points, a delta of 67.4 percent. The consistency of these two deltas, 67.5 and 67.4 percent, suggests that the performance separation is structural rather than workload-specific. Whether the API is OpenCL or Vulkan, the GTX 970 roughly triples the output of the GTX 950M.

Looking beyond the head-to-head tests, the broader database picture reinforces this hierarchy. The GTX 950M posts an average benchmark score of 8,135, placing it at the 42nd percentile of all GPUs. Its nearest rivals include the AMD Radeon R9 M360 (8,129, a 0.1 percent difference), the NVIDIA GeForce GTX 980 (8,167, a 0.4 percent deficit), the NVIDIA GeForce 945M (8,099, a 0.4 percent advantage), and the NVIDIA GRID K2 (8,080, a 0.7 percent edge). The GTX 950M sits in a tight cluster where a few percent separates it from its immediate competitors, and it trades blows with the R9 M360 and GeForce 945M within a single percentage point.

The GTX 970, by contrast, shows a more unusual positioning in the database. Its average benchmark score is 7,157, which places it at the 39th percentile of all GPUs, slightly below the GTX 950M's percentile ranking despite its overwhelming head-to-head victories. Its nearest rivals are the Intel Iris Pro Graphics P580 (7,170, a 0.2 percent deficit), the NVIDIA GeForce GTX 560 SE (7,171, a 0.2 percent deficit), the AMD Radeon Vega 8 Mobile (7,203, a 0.6 percent deficit), and the NVIDIA GeForce GTX 750 (7,222, a 0.9 percent deficit). The GTX 970 trails each of these by less than one percent, a remarkable outcome for a card that crushes the GTX 950M by more than two-thirds in direct comparison.

The explanation lies in the composition of the benchmark suites. The GTX 970 has 11 recorded benchmark entries spanning DirectX 9, DirectX 10, DirectX 11, DirectX 12, Metal, OpenCL, Vulkan, G2D, G3D, and compute workloads. Its Passmark G3D score of 9,638 and Passmark GPU Compute score of 4,073 are respectable, but its DirectX 9 score of 143, DirectX 10 score of 46, DirectX 11 score of 71, and DirectX 12 score of 41 drag the average down. The GTX 950M, with only two benchmark entries (both in Geekbench), benefits from an average that reflects only its strongest workloads. This is a case where the aggregate score tells a different story than the direct comparison, and the direct comparison is the more reliable indicator of relative capability.

FAQ

Q: Which GPU wins the Geekbench OpenCL benchmark?

A: The NVIDIA GeForce GTX 970 wins decisively with 29,982 points versus 9,745 points for the GTX 950M, a 67.5 percent advantage.

Q: Is the GTX 950M competitive with the GTX 970 in Vulkan performance?

A: No. The GTX 970 scores 20,005 points in Geekbench Vulkan, while the GTX 950M scores 6,525 points, a 67.4 percent gap. The GTX 970 is roughly three times faster.

Q: How does the GTX 970 compare to its nearest rivals in the database?

A: The GTX 970's average benchmark score of 7,157 places it slightly behind the Intel Iris Pro Graphics P580 (7,170, 0.2 percent behind), the NVIDIA GeForce GTX 560 SE (7,171, 0.2 percent behind), the AMD Radeon Vega 8 Mobile (7,203, 0.6 percent behind), and the NVIDIA GeForce GTX 750 (7,222, 0.9 percent behind). All four rivals edge it out by less than one percent.

Q: What are the GTX 950M's closest competitors according to the database?

A: The AMD Radeon R9 M360 (8,129, 0.1 percent behind), the NVIDIA GeForce GTX 980 (8,167, 0.4 percent ahead), the NVIDIA GeForce 945M (8,099, 0.4 percent behind), and the NVIDIA GRID K2 (8,080, 0.7 percent behind) are its nearest rivals. The GTX 950M's average score is 8,135.

Q: Does the GTX 950M have a higher percentile ranking than the GTX 970?

A: Yes. The GTX 950M sits at the 42nd percentile of all GPUs, while the GTX 970 sits at the 39th percentile. This reflects the different benchmark compositions rather than actual performance equivalence.

Q: Which card has more recorded benchmarks in the database?

A: The GTX 970 has 11 recorded benchmark results, covering Passmark DirectX 9, 10, 11, and 12, Passmark G2D, G3D, and GPU Compute, Geekbench Metal, OpenCL, and Vulkan, plus 3DMark Steel Nomad DX12. The GTX 950M has only two: Geekbench OpenCL and Geekbench Vulkan.

Architecture Differences

The two GPUs represent distinct branches of the Maxwell family. The GTX 950M uses the GM107 chip, built on the original Maxwell architecture, while the GTX 970 uses the GM204 chip, built on Maxwell 2.0. Both are manufactured by TSMC on a 28 nm process, but the similarities end there.

The transistor counts reveal the scale of the architectural gap. The GM107 packs 1,870 million transistors into a 148 mm² die, yielding a transistor density of 12.6 million transistors per square millimeter. The GM204 is a substantially larger design, with 5,200 million transistors spread across 398 mm², for a density of 13.1 million per square millimeter. The GTX 970's chip contains nearly three times the transistor budget of the GTX 950M, and it uses that budget to field far more execution resources.

The compute configuration tells the story in raw numbers. The GTX 950M has 640 shading units, 40 texture mapping units, and 16 raster operation pipelines. The GTX 970 more than doubles the shading units to 1,664, more than doubles the TMUs to 104, and more than triples the ROPs to 56. These are not incremental upgrades; they are category-defining differences. A shader count of 1,664 versus 640 means the GTX 970 can process far more parallel work per clock, and the 56 ROPs versus 16 means it can push dramatically more pixels to the display.

The memory subsystems diverge as sharply as the compute cores. The GTX 950M uses 4 GB of DDR3 memory on a 128 bit bus, delivering 28.80 GB/s of bandwidth. The GTX 970 uses 4 GB of GDDR5 memory on a 256 bit bus, delivering 224.4 GB/s. That is nearly an eightfold increase in memory bandwidth, which directly impacts texture-heavy workloads, high-resolution rendering, and compute tasks that stream large datasets. The GTX 950M's memory runs at 900 MHz (1,800 Mbps effective), while the GTX 970's memory runs at 1,753 MHz (7 Gbps effective).

Clock speeds also favor the GTX 970. The desktop card has a base clock of 1,050 MHz and a boost clock of 1,178 MHz, against the GTX 950M's 993 MHz base and 1,124 MHz boost. The combination of higher clocks and far more execution units produces the massive throughput gap seen in the benchmarks. The GTX 970's pixel rate is 65.97 GPixel/s versus 17.98 GPixel/s for the GTX 950M, and its texture rate is 122.5 GTexel/s versus 44.96 GTexel/s. In FP32 compute, the GTX 970 delivers 3.920 TFLOPS against the GTX 950M's 1,438.7 GFLOPS.

API support differs in one notable respect. The GTX 950M supports DirectX 12 (11_0), while the GTX 970 supports DirectX 12 (12_1). Both cards support OpenGL 4.6 and Vulkan 1.4. The GTX 970's higher DirectX feature level reflects its newer Maxwell 2.0 design and gives it access to additional rendering features in titles that use DirectX 12_1.

Specification Differences

The two cards differ across nearly every specification field in the database. The GTX 950M uses the GM107 chip, while the GTX 970 uses the GM204. The GTX 950M belongs to the GeForce 900M generation, while the GTX 970 belongs to the GeForce 900 generation. The GTX 950M's predecessor is the GeForce 800M and its successor is the GeForce 10 Mobile; the GTX 970's predecessor is the GeForce 700 and its successor is the GeForce 10.

The GTX 950M has a TDP of 75 W and uses an IGP slot width with no power connectors. The GTX 970 has a TDP of 148 W, uses a dual-slot cooler, and requires two 6-pin power connectors. The GTX 970 also lists a suggested PSU of 300 W, while the GTX 950M has no suggested PSU in the database. The bus interface differs as well: the GTX 950M uses PCIe 3.0 x8, while the GTX 970 uses PCIe 3.0 x16.

Memory specifications diverge completely. The GTX 950M has 4 GB of DDR3 on a 128 bit bus with 28.80 GB/s bandwidth. The GTX 970 has 4 GB of GDDR5 on a 256 bit bus with 224.4 GB/s bandwidth. The GTX 950M's memory clock is 900 MHz (1,800 Mbps effective), while the GTX 970's is 1,753 MHz (7 Gbps effective).

The GTX 970 has physical dimensions recorded in the database: 267 mm (10.5 inches) in length, 111 mm (4.4 inches) in height, and 40 mm (1.6 inches) in width. The GTX 950M has no recorded dimensions, consistent with its IGP form factor and portable-device-dependent display outputs. The GTX 970's display outputs are listed as 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.2, while the GTX 950M's outputs depend on the portable device it is integrated into.

Release dates place the GTX 970 first: September 18, 2014, versus March 12, 2015 for the GTX 950M. The GTX 970 has a launch MSRP of 329 USD. The GTX 950M has no launch MSRP recorded. Both cards are end-of-life products.

The Verdict

The data supports a straightforward conclusion for most users: the GTX 970 is the overwhelmingly faster GPU. In both recorded head-to-head benchmarks, it leads by roughly 67 percent, and its compute resources, memory bandwidth, and clock speeds all point in the same direction. Anyone choosing between these two for raw performance should select the GTX 970 without hesitation.

The GTX 950M's case rests on different grounds. At 75 W with no power connectors and an IGP slot width, it is designed for portable devices where power draw and physical space are constrained. The GTX 970 demands 148 W, a dual-slot cooler, two 6-pin power connectors, and a 300 W suggested PSU. The GTX 950M is the only viable option in a laptop or compact integrated system; the GTX 970 is a desktop component with substantial power and cooling requirements.

The GTX 970's 329 USD launch MSRP positions it as a mid-range desktop card, and its 4 GB GDDR5 memory with 224.4 GB/s bandwidth gives it a massive advantage in bandwidth-sensitive workloads. The GTX 950M's 4 GB DDR3 memory with 28.80 GB/s bandwidth is a severe bottleneck by comparison, and its 128 bit bus limits its ability to feed its 640 shading units.

Curiously, the database's aggregate scores tell a different story than the direct benchmarks. The GTX 950M's average score of 8,135 exceeds the GTX 970's 7,157, and the GTX 950M ranks at the 42nd percentile versus the GTX 970's 39th. This is an artifact of benchmark selection: the GTX 950M has only two Geekbench entries, both of which are its strongest tests, while the GTX 970's 11 entries include several low DirectX scores that drag its average down. Buyers should weight the head-to-head results more heavily than the aggregate, as the direct comparison is the only test where both cards run identical workloads.

For a desktop builder with a proper power supply and case space, the GTX 970 is the clear pick. Its 1,664 shading units, 56 ROPs, and 3.920 TFLOPS of FP32 compute put it in a different league from the GTX 950M's 640 shading units, 16 ROPs, and 1,438.7 GFLOPS. For a laptop buyer who needs a discrete GPU in a thin chassis, the GTX 950M is the only one of the two that fits, and its 42nd percentile ranking shows it is a competent mid-tier mobile part. The verdict, strictly from the data, is that the GTX 970 is the superior performer, while the GTX 950M serves a completely different form factor with appropriately scaled expectations.