NVIDIA GeForce 920M vs NVIDIA GeForce GTX 750 Ti Comparison

The NVIDIA GeForce 920M and the NVIDIA GeForce GTX 750 Ti represent two very different tiers of graphics hardware, despite both being NVIDIA products from a similar era. The 920M is a mobile-integrated part designed for basic laptop tasks, while the GTX 750 Ti is a dedicated desktop card built for gaming. The benchmark data shows a decisive performance gap, with the GTX 750 Ti winning all head-to-head comparisons by a wide margin, though the 920M holds its own in specific low-power contexts.

Head-to-Head Benchmarks

The two available head-to-head benchmark results paint an unambiguous picture of the performance hierarchy between these GPUs. In the Geekbench OpenCL test, the NVIDIA GeForce GTX 750 Ti scores 10,827 points, while the GeForce 920M manages only 3,725 points. This represents a delta of -65.6% for the 920M, meaning the GTX 750 Ti is roughly 2.9 times faster in raw compute workloads. The OpenCL test is particularly relevant for general-purpose GPU compute, so this gap reflects not just gaming performance but also any application that offloads parallel processing to the graphics card.

The Vulkan benchmark shows an even wider disparity. Here, the GTX 750 Ti posts a score of 10,065, versus the 920M's 2,849. The delta of -71.7% indicates that the GTX 750 Ti delivers over 3.5 times the performance in this low-level graphics API. Vulkan is known for efficient CPU overhead and is used in modern games and compute applications, so this result strongly suggests the GTX 750 Ti will provide a dramatically smoother experience in Vulkan-based titles.

Looking at the broader benchmark context, the average benchmark score for the 920M is 3,287, while the GTX 750 Ti averages 2,953. This is interesting because it appears to contradict the head-to-head results. The explanation lies in the test suites: the 920M has only Geekbench scores, whereas the GTX 750 Ti includes a wider range of tests, including PassMark DirectX 9/10/11/12 tests that score very low (ranging from 17 to 60). These low DirectX scores drag down the GTX 750 Ti's average, even though its compute and modern-API performance is far superior. The 920M's percentile rank is 20, while the GTX 750 Ti sits at 19, further illustrating that these averages can be misleading without considering the test composition.

The nearestRivals data provides additional context. The 920M's closest competitor is the GeForce GT 730M, which has an average score of 3,316 and a delta of -0.9% — essentially a tie. The GTX 750 Ti's nearest rival is the GeForce GTX 860M, with an average score of 2,967 and a delta of -0.5%. This shows that the GTX 750 Ti sits in a performance tier roughly equivalent to a mid-range laptop GPU from the same generation, while the 920M is closer to entry-level integrated graphics.

FAQ

Q: Which GPU is faster in the Geekbench OpenCL benchmark?

A: The NVIDIA GeForce GTX 750 Ti is significantly faster, scoring 10,827 compared to the 920M's 3,725. The delta is -65.6% from the 920M's perspective, meaning the GTX 750 Ti is nearly three times faster.

Q: How do these GPUs compare in Vulkan performance?

A: The GTX 750 Ti dominates the Vulkan test with a score of 10,065 versus the 920M's 2,849. This -71.7% delta indicates the GTX 750 Ti is over 3.5 times faster in this modern graphics API.

Q: Why does the 920M have a higher average benchmark score than the GTX 750 Ti?

A: The 920M's average is 3,287, while the GTX 750 Ti averages 2,953. This is because the 920M only has Geekbench scores, while the GTX 750 Ti includes PassMark tests with very low scores (ranging from 17 to 60) that pull its average down despite its superior performance in other tests.

Q: What are the percentile rankings for these GPUs?

A: The 920M ranks in the 20th percentile of all GPUs, while the GTX 750 Ti ranks in the 19th percentile. Despite the GTX 750 Ti's massive wins in head-to-head tests, its overall percentile is slightly lower due to the broader test suite.

Q: Which GPU has a higher transistor density?

A: The GTX 750 Ti has a higher transistor density at 12.6M per mm², compared to the 920M's 11.7M per mm². However, both use the same 28 nm process node from TSMC.

Q: What is the memory bandwidth difference between these cards?

A: The GTX 750 Ti offers 86.40 GB/s of bandwidth, while the 920M provides only 14.40 GB/s. This is a massive difference that directly impacts texture streaming and high-resolution performance.

Architecture Differences

The two GPUs are built on fundamentally different architectures. The 920M uses GK208B, which is based on Kepler 2.0, while the GTX 750 Ti uses GM107, based on Maxwell. This architectural shift is significant, as Maxwell introduced several efficiency improvements over Kepler, including better scheduling and reduced power consumption per unit of performance.

Transistor counts reflect this difference. The GTX 750 Ti packs 1,870 million transistors into a 148 mm² die, while the 920M has 1,020 million transistors on a smaller 87 mm² die. The transistor density is slightly higher on the GTX 750 Ti at 12.6M per mm² versus 11.7M per mm², but both are produced on the same 28 nm TSMC process. This means the GTX 750 Ti's advantage comes from both more silicon and a more efficient architecture.

The memory subsystems are also architecturally distinct. The 920M uses DDR3 memory on a 64-bit bus, yielding 14.40 GB/s bandwidth, while the GTX 750 Ti uses GDDR5 on a 128-bit bus, achieving 86.40 GB/s — exactly six times the bandwidth. This is not just a larger number; it changes what workloads are feasible. The GTX 750 Ti can handle high-resolution textures and multi-sample anti-aliasing without starving the GPU, whereas the 920M would bottleneck quickly.

Both GPUs support DirectX 12 (11_0), OpenGL 4.6, and Vulkan, though with different version numbers for Vulkan. The 920M supports Vulkan 1.2.175, while the GTX 750 Ti supports Vulkan 1.4. This newer Vulkan version on the GTX 750 Ti may offer additional features and optimizations.

Specification Differences

The specification sheet reveals several clear distinctions. The GTX 750 Ti has 640 shading units, 40 texture mapping units, and 16 ROPs, while the 920M has 384 shading units, 32 TMUs, and only 8 ROPs. This translates to a pixel rate of 17.36 GPixel/s for the GTX 750 Ti versus 7.632 GPixel/s for the 920M, and a texture rate of 43.40 GTexel/s versus 30.53 GTexel/s. The FP32 compute throughput is 1,388.8 GFLOPS on the GTX 750 Ti, nearly double the 920M's 732.7 GFLOPS.

Clock speeds also differ. The GTX 750 Ti runs at a base clock of 1020 MHz with a boost of 1085 MHz, while the 920M is locked at 954 MHz for both base and boost. Memory clocks are even more divergent: the GTX 750 Ti's memory runs at 1350 MHz (5.4 Gbps effective), while the 920M's runs at 900 MHz (1800 Mbps effective).

Power and physical characteristics separate them further. The 920M is an integrated part with a 33 W TDP, no power connectors, and an IGP slot width, designed to be soldered onto a laptop motherboard. The GTX 750 Ti is a discrete card with a 60 W TDP, a single-slot form factor, and a length of 145 mm (5.7 inches). It also has a suggested PSU of 250 W, while the 920M has no such requirement. The bus interface differs as well: the 920M uses PCIe 3.0 x8, while the GTX 750 Ti uses PCIe 3.0 x16. Display outputs are also different, with the 920M being "Portable Device Dependent" and the GTX 750 Ti offering 2x DVI and 1x mini-HDMI 1.4a.

The Verdict

The data is clear: the GTX 750 Ti is the superior performer in every head-to-head benchmark. Its 65.6% lead in OpenCL and 71.7% lead in Vulkan are not marginal improvements — they represent a different performance class entirely. The GTX 750 Ti's architecture, memory bandwidth, and compute resources are all substantially better, making it the obvious choice for any task that requires graphical or compute performance.

However, context matters. The 920M is a mobile integrated GPU with a 33 W TDP, designed for thin-and-light laptops where power efficiency is paramount. Its nearest rival is the GT 730M, which it matches within 0.9%, and it outperforms the GT 640 by 2.4%. This suggests the 920M is perfectly adequate for basic 2D acceleration, video playback, and light productivity workloads. The GTX 750 Ti, with its 60 W TDP and dedicated card form factor, is not a direct competitor in the same physical or power envelope.

For a desktop user who wants to play games or use GPU-accelerated applications, the GTX 750 Ti is the only rational choice. Its Vulkan 1.4 support and massive bandwidth advantage make it future-proof for modern titles. For a laptop user who needs basic graphics without battery drain, the 920M serves its purpose, though it will struggle with anything beyond light gaming.

Where Each One Wins

The GTX 750 Ti wins in every measurable performance category. Its OpenCL score of 10,827 versus 3,725 means it dominates compute workloads like video encoding, rendering, and scientific calculations. Its Vulkan score of 10,065 versus 2,849 means it handles modern games and applications that leverage this API with ease. The 86.40 GB/s memory bandwidth versus 14.40 GB/s is a decisive advantage in any bandwidth-sensitive task, from high-resolution textures to large data sets in compute shaders.

The 920M's wins are more subtle and relate to factors not captured in raw benchmark scores. Its 33 W TDP versus the GTX 750 Ti's 60 W means it generates less heat and consumes less power, making it suitable for compact laptops without active cooling solutions. Its IGP form factor means it has no physical footprint beyond the motherboard, whereas the GTX 750 Ti requires a PCIe slot and a 250 W PSU. The 920M's release date of March 2015 also makes it a later product than the GTX 750 Ti's February 2014 launch, though both are now end-of-life.

In specific workloads, the GTX 750 Ti's PassMark scores provide additional insight. It scores 3,903 in PassMark G3D, 1,744 in GPU compute, and 528 in G2D. These are respectable numbers that confirm its gaming and compute viability. The 920M has no equivalent PassMark data, but its Geekbench scores suggest it falls short of the GTX 750 Ti's capabilities by a wide margin. For users who prioritize performance, the GTX 750 Ti is the clear winner; for users who prioritize portability and power efficiency, the 920M is the more appropriate — albeit less capable — option.