NVIDIA GeForce 940MX vs NVIDIA GeForce GTX 970M Comparison

The NVIDIA GeForce 940MX and GTX 970M are both end-of-life mobile graphics solutions from NVIDIA’s GeForce 900M generation, but the benchmark data reveals a stark performance gulf between them. Based on the two shared head-to-head tests, the GTX 970M decisively outperforms the 940MX, making it the clear choice for demanding workloads. However, the 940MX holds its own in specific low-power and legacy scenarios, offering a distinct set of trade-offs that are worth examining.

Head-to-Head Benchmarks

The most telling comparison comes from the Geekbench compute tests, which are the only two benchmarks shared by both GPUs. In the Geekbench OpenCL test, the GTX 970M scores 18,946 against the 940MX’s 4,939. This represents a 73.9% lead for the GTX 970M, a massive margin that underscores the difference in raw compute throughput. The 940MX is essentially outclassed here, finishing far behind its larger sibling.

The Geekbench Vulkan test tells a similar story. The GTX 970M posts a score of 18,292, while the 940MX manages just 4,749. The delta is 74% in favor of the GTX 970M, confirming that the performance gap is consistent across different graphics APIs. These aren’t marginal differences; the GTX 970M is delivering roughly four times the performance in both tests.

Looking at the broader benchmark context, the 940MX’s average benchmark score is 4,844, while the GTX 970M’s average is 4,628. This is surprising at first glance, given the GTX 970M’s dominance in the head-to-head tests. The discrepancy arises because the GTX 970M’s average is dragged down by its inclusion of multiple Passmark tests — including DirectX 9, 10, 11, 12, G2D, G3D, and GPU compute scores — many of which are low (e.g., 28 in DirectX 10, 42 in DirectX 11, 24 in DirectX 12). The 940MX only has the two Geekbench tests, which are comparatively high for its class. As such, the average scores are not directly comparable, but the head-to-head data is unambiguous: the GTX 970M wins both shared tests outright.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The 940MX has a higher average benchmark score of 4,844 compared to the GTX 970M’s 4,628. However, this is misleading because the GTX 970M’s average includes many low-scoring Passmark tests, while the 940MX only has two Geekbench results.

Q: How much faster is the GTX 970M in OpenCL compute?

A: The GTX 970M scores 18,946 in Geekbench OpenCL, which is 73.9% higher than the 940MX’s score of 4,939. This indicates a substantial advantage in general-purpose compute workloads.

Q: Does the 940MX beat the GTX 970M in any shared benchmark?

A: No. In the two head-to-head benchmarks (Geekbench OpenCL and Vulkan), the GTX 970M wins both. The 940MX has zero wins in the head-to-head comparison.

Q: What is the performance percentile ranking for each GPU?

A: The 940MX ranks in the 28th percentile of all GPUs, while the GTX 970M ranks in the 27th percentile. Despite the GTX 970M’s superior performance in direct tests, both sit near the bottom quartile of the overall GPU landscape.

Q: Are there any rival GPUs that perform similarly to the 940MX?

A: Yes. The 940MX’s nearest rivals include the NVIDIA GeForce GTX 560M with an average score of 4,855 (just 0.2% higher), the AMD Radeon R6 M255DX at 4,867 (0.5% higher), and the NVIDIA GeForce GTS 450 at 4,893 (1% higher). Interestingly, the NVIDIA GeForce RTX 3080 12 GB appears as a rival with a score of 4,791, which is 1.1% lower.

Q: What about the GTX 970M’s nearest competitors?

A: The GTX 970M’s nearest rivals include the NVIDIA Quadro M3000M at 4,621 (0.2% higher), the AMD Radeon R5 M320 at 4,657 (0.6% higher), and the AMD Radeon RX 9060 XT 16 GB at 4,657 (0.6% higher). The AMD Radeon R5 M230 scores 4,577, which is 1.1% lower.

Architecture Differences

The two GPUs are built on the same 28 nm process at TSMC, but they use different chips and architectures. The 940MX is based on the GM107 chip using the original Maxwell architecture, while the GTX 970M uses the GM204 chip with the more refined Maxwell 2.0 architecture. This architectural leap is significant: Maxwell 2.0 brings improvements in geometry processing and tessellation efficiency, which helps the GTX 970M handle more complex scenes.

The transistor counts tell a story of scale. The 940MX packs 1,870 million transistors on a 148 mm² die, resulting in a density of 12.6 million transistors per mm². The GTX 970M, by contrast, has 5,200 million transistors on a 398 mm² die, with a slightly higher density of 13.1 million transistors per mm². The GTX 970M’s larger die is not just about more transistors; it also means more execution resources.

In terms of compute units, the 940MX has 512 shading units, 32 texture mapping units (TMUs), and 8 render output units (ROPs). The GTX 970M scales this up dramatically with 1,280 shading units, 80 TMUs, and 48 ROPs. This 2.5x increase in shading units and 6x increase in ROPs directly translates to the higher fill rates and compute performance observed in benchmarks. Both GPUs lack dedicated ray tracing cores and tensor cores, as neither Maxwell architecture supports these features.

Specification Differences

The most obvious difference is memory configuration. The 940MX comes with 2 GB of GDDR5 memory on a 64-bit bus, delivering 40.10 GB/s of bandwidth. The GTX 970M offers 6 GB of GDDR5 on a 192-bit bus, tripling the bus width and boosting bandwidth to 120.3 GB/s. Higher bandwidth is critical for high-resolution textures and multi-sample anti-aliasing, areas where the GTX 970M clearly excels.

Clock speeds also diverge. The 940MX runs at a base clock of 795 MHz with a boost clock of 861 MHz, while the GTX 970M operates at 924 MHz base and 1,038 MHz boost. Both share the same memory clock of 1253 MHz (effectively 5 Gbps). The GTX 970M’s higher core clocks contribute to its superior pixel and texture rates: the 940MX achieves 6.888 GPixel/s and 27.55 GTexel/s, whereas the GTX 970M reaches 49.82 GPixel/s and 83.04 GTexel/s.

Compute performance (FP32) is another major differentiator. The 940MX delivers 881.7 GFLOPS of single-precision performance, while the GTX 970M delivers 2.657 TFLOPS — a threefold increase. The GTX 970M also features a higher-tier DirectX support, listing DirectX 12 (12_1) compared to the 940MX’s DirectX 12 (11_0). Both support OpenGL 4.6 and Vulkan 1.4. Power draw is specified only for the 940MX at 23 W; the GTX 970M’s TDP is not listed. The bus interface differs as well: the 940MX uses PCIe 3.0 x8, while the GTX 970M uses MXM-B (3.0). Both are MXM modules with no power connectors and portable-device-dependent display outputs.

Where Each One Wins

The GTX 970M wins in virtually every performance-oriented scenario. Its 6 GB of VRAM and 120.3 GB/s bandwidth make it suitable for gaming at higher resolutions and detail settings, as well as for GPU-accelerated rendering and video editing. The 74% lead in both OpenCL and Vulkan benchmarks positions it as the go-to choice for compute-heavy tasks like 3D modeling or scientific simulations. The higher pixel rate (49.82 GPixel/s) means it can drive more demanding display outputs, and the superior texture rate (83.04 GTexel/s) ensures smoother texture filtering in modern games.

The 940MX wins in scenarios where power efficiency and simplicity are paramount. Its 23 W TDP is dramatically lower than the GTX 970M’s unspecified but presumably higher draw, making it ideal for thin-and-light laptops where battery life and thermals are constrained. The 2 GB memory and 64-bit bus are adequate for light productivity, web browsing, and older or less demanding titles. Its lower core count (512 shading units) and clock speeds mean it generates less heat, which can be a boon in compact chassis. The 940MX is also the more recent release, with a launch date of 2016-06-27 versus the GTX 970M’s 2014-10-06, so it may have better driver optimization for contemporary software at the time of release.

For users who need to run modern games or GPU-intensive applications, the GTX 970M is the only viable option here. For users who prioritize portability, silent operation, and basic multimedia tasks, the 940MX offers a lower-power alternative. The data is clear: the GTX 970M dominates the shared benchmarks, but the 940MX remains a serviceable entry-level part with a distinct niche.